The paper presents to address this challenge, we have proposed the use of Adaptive Window Positioning
technique which focuses on not just the meaning of the handwritten signature but also on the individuality
of the writer. This innovative technique divides the handwritten signature into 13 small windows of size nxn
(13x13). This size should be large enough to contain ample information about the style of the author and
small enough to ensure a good identification performance. The process was tested with a GPDS dataset
containing 4870 signature samples from 90 different writers by comparing the robust features of the test
signature with that of the user’s signature using an appropriate classifier. Experimental results reveal that
adaptive window positioning technique proved to be the efficient and reliable method for accurate
signature feature extraction for the identification of offline handwritten signatures .The contribution of this
technique can be used to detect signatures signed under emotional duress
Offline signature identification using high intensity variations and cross ov...eSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
A Review on Robust identity verification using signature of a personEditor IJMTER
Signature is behavioural type biometrics characteristics of human. Signature has been a
distinguishing feature for person identification. In these days increasing number of transactions,
especially related to financial and business are being authorized via signatures. Two types of
verification methods are: Offline signature verification and online signature verification. In this paper
we review various components of offline signature reorganization and verification system, feature
extraction techniques and available techniques.
This slide proposed a method to authenticate a signature in off-line. Our proposed method uses "Harris Corner Detector", "Orientation Assignment" , "KNN Classifier", "Hungarian Algorithm".
An offline signature verification using pixels intensity levelsSalam Shah
Offline signature recognition has great importance in our day to day activities. Researchers are trying to use them as biometric identification in various areas like banks, security systems and for other identification purposes. Fingerprints, iris, thumb impression and face detection based biometrics are successfully used for identification of individuals because of their static nature. However, people’s signatures show variability that makes it difficult to recognize the original signatures correctly and to use them as biometrics. The handwritten signatures have importance in banks for cheque, credit card processing, legal and financial transactions, and the signatures are the main target of fraudulence. To deal with complex signatures, there should be a robust signature verification method in places such as banks that can correctly classify the signatures into genuine or forgery to avoid financial frauds. This paper, presents a pixels intensity level based offline signature verification model for the correct classification of signatures. To achieve the target, three statistical classifiers; Decision Tree (J48), probability based Naïve Bayes (NB tree) and Euclidean distance based k-Nearest Neighbor (IBk), are used.
For comparison of the accuracy rates of offline signatures with online signatures, three classifiers were applied on online signature database and achieved a 99.90% accuracy rate with decision tree (J48), 99.82% with Naïve Bayes Tree and 98.11% with K-Nearest Neighbor (with 10 fold cross validation). The results of offline signatures were 64.97% accuracy rate with decision tree (J48), 76.16% with Naïve Bayes Tree and 91.91% with k-Nearest Neighbor (IBk) (without forgeries). The accuracy rate dropped with the inclusion of forgery signatures as, 55.63% accuracy rate with decision tree (J48), 67.02% with Naïve Bayes Tree and 88.12% (with forgeries).
Offline Handwritten Signature Identification and Verification using Multi-Res...CSCJournals
In this paper, we are proposing a new method for offline (static) handwritten signature identification and verification based on Gabor wavelet transform. The whole idea is offering a simple and robust method for extracting features based on Gabor Wavelet which the dependency of the method to the nationality of signer has been reduced to its minimal. After pre-processing stage that contains noise reduction and signature image normalisation by size and rotation, a virtual grid is placed on the signature image. Gabor wavelet coefficients with different frequencies and directions are computed on each points of this grid and then fed into a classifier. The shortest weighted distance has been used as the classifier. The weight that is used as the coefficient for computing the shortest distance is based on the distribution of instances in each of signature classes. As it was pointed out earlier, one of the advantages of this system is its capability of signature identification and verification of different nationalities; thus it has been tested on four signature dataset with different nationalities including Iranian, Turkish, South African and Spanish signatures. Experimental results and the comparison of the proposed system with other systems are consistent with desirable outcomes. Despite the use of the simplest method of classification i.e. the nearest neighbour, the proposed algorithm in comparison with other algorithms has very good capabilities. Comparing the results of our system with the accuracy of human\'s identification and verification, it shows that human identification is more accurate but our proposed system has a lower error rate in verification.
Authentication of a person is the major concern in this era for security purposes. In biometric systems Signature is one of the behavioural features used for the authentication purpose. In this paper we work on the offline signature collected through different persons. Morphological operations are applied on these signature images with Hough transform to determine regular shape which assists in authentication process. The values extracted from this Hough space is used in the feed forward neural network which is trained using back-propagation algorithm. After the different training stages efficiency found above more than 95%. Application of this system will be in the security concerned fields, in the defence security, biometric authentication, as biometric computer protection or as method of the analysis of person’s behaviour changes.
Offline signature identification using high intensity variations and cross ov...eSAT Publishing House
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
A Review on Robust identity verification using signature of a personEditor IJMTER
Signature is behavioural type biometrics characteristics of human. Signature has been a
distinguishing feature for person identification. In these days increasing number of transactions,
especially related to financial and business are being authorized via signatures. Two types of
verification methods are: Offline signature verification and online signature verification. In this paper
we review various components of offline signature reorganization and verification system, feature
extraction techniques and available techniques.
This slide proposed a method to authenticate a signature in off-line. Our proposed method uses "Harris Corner Detector", "Orientation Assignment" , "KNN Classifier", "Hungarian Algorithm".
An offline signature verification using pixels intensity levelsSalam Shah
Offline signature recognition has great importance in our day to day activities. Researchers are trying to use them as biometric identification in various areas like banks, security systems and for other identification purposes. Fingerprints, iris, thumb impression and face detection based biometrics are successfully used for identification of individuals because of their static nature. However, people’s signatures show variability that makes it difficult to recognize the original signatures correctly and to use them as biometrics. The handwritten signatures have importance in banks for cheque, credit card processing, legal and financial transactions, and the signatures are the main target of fraudulence. To deal with complex signatures, there should be a robust signature verification method in places such as banks that can correctly classify the signatures into genuine or forgery to avoid financial frauds. This paper, presents a pixels intensity level based offline signature verification model for the correct classification of signatures. To achieve the target, three statistical classifiers; Decision Tree (J48), probability based Naïve Bayes (NB tree) and Euclidean distance based k-Nearest Neighbor (IBk), are used.
For comparison of the accuracy rates of offline signatures with online signatures, three classifiers were applied on online signature database and achieved a 99.90% accuracy rate with decision tree (J48), 99.82% with Naïve Bayes Tree and 98.11% with K-Nearest Neighbor (with 10 fold cross validation). The results of offline signatures were 64.97% accuracy rate with decision tree (J48), 76.16% with Naïve Bayes Tree and 91.91% with k-Nearest Neighbor (IBk) (without forgeries). The accuracy rate dropped with the inclusion of forgery signatures as, 55.63% accuracy rate with decision tree (J48), 67.02% with Naïve Bayes Tree and 88.12% (with forgeries).
Offline Handwritten Signature Identification and Verification using Multi-Res...CSCJournals
In this paper, we are proposing a new method for offline (static) handwritten signature identification and verification based on Gabor wavelet transform. The whole idea is offering a simple and robust method for extracting features based on Gabor Wavelet which the dependency of the method to the nationality of signer has been reduced to its minimal. After pre-processing stage that contains noise reduction and signature image normalisation by size and rotation, a virtual grid is placed on the signature image. Gabor wavelet coefficients with different frequencies and directions are computed on each points of this grid and then fed into a classifier. The shortest weighted distance has been used as the classifier. The weight that is used as the coefficient for computing the shortest distance is based on the distribution of instances in each of signature classes. As it was pointed out earlier, one of the advantages of this system is its capability of signature identification and verification of different nationalities; thus it has been tested on four signature dataset with different nationalities including Iranian, Turkish, South African and Spanish signatures. Experimental results and the comparison of the proposed system with other systems are consistent with desirable outcomes. Despite the use of the simplest method of classification i.e. the nearest neighbour, the proposed algorithm in comparison with other algorithms has very good capabilities. Comparing the results of our system with the accuracy of human\'s identification and verification, it shows that human identification is more accurate but our proposed system has a lower error rate in verification.
Authentication of a person is the major concern in this era for security purposes. In biometric systems Signature is one of the behavioural features used for the authentication purpose. In this paper we work on the offline signature collected through different persons. Morphological operations are applied on these signature images with Hough transform to determine regular shape which assists in authentication process. The values extracted from this Hough space is used in the feed forward neural network which is trained using back-propagation algorithm. After the different training stages efficiency found above more than 95%. Application of this system will be in the security concerned fields, in the defence security, biometric authentication, as biometric computer protection or as method of the analysis of person’s behaviour changes.
Freeman Chain Code (FCC) Representation in Signature Fraud Detection Based On...CSCJournals
This paper presents a signature verification system that used Freeman Chain Code (FCC) as directional feature and data representation. There are 47 features were extracted from the signature images from six global features. Before extracting the features, the raw images were undergoing pre-processing stages which were binarization, noise removal by using media filter, cropping and thinning to produce Thinned Binary Image (TBI). Euclidean distance is measured and matched between nearest neighbours to find the result. MCYT-SignatureOff-75 database was used. Based on our experiment, the lowest FRR achieved is 6.67% and lowest FAR is 12.44% with only 1.12 second computational time from nearest neighbour classifier. The results are compared with Artificial Neural Network (ANN) classifier.
An appraisal of offline signature verification techniquesSalam Shah
Biometrics is being commonly used nowadays for the identification and verification of humans everywhere in the world. In biometrics humans unique characteristics like palm, fingerprints, iris etc. are being used. Pattern Recognition and image processing are the major areas where research on signature verification is carried out. Hand written Signature of an individual is also unique and for identification of humans are being used and accepted specially in the banking and other financial transactions. The hand written signatures due to its importance are at target of fraudulence. In this paper we have surveyed different papers on techniques that are currently used for the identification and verification of Offline signatures.
Fraud Detection Using Signature RecognitionTejraj Thakor
The signature of person is an important bio metric of a human being which can be used to authenticate human identity. The problem arises when someone decide to imitate our signature and steal our identity.
The Image of human signature is collected by camera of mobile phone which can extract dynamic and spatial information of the signature based on Image processing techniques like Convert to gray scale, Noise Removal, Normalization, Border Elimination and Feature Extraction techniques.
The signature matching is depending on SVM. The SVM classifier is trained with sample images in database obtained from those individuals whose signatures have to be authenticated by the system. In our proposed system SQLite database as a back-end and Android platform as a front-end.
OFFLINE SIGNATURE RECOGNITION VIA CONVOLUTIONAL NEURAL NETWORK AND MULTIPLE C...IJNSA Journal
One of the most important processes used by companies to safeguard the security of information and prevent it from unauthorized access or penetration is the signature process. As businesses and individuals move into the digital age, a computerized system that can discern between genuine and faked signatures is crucial for protecting people's authorization and determining what permissions they have. In this paper, we used Pre-Trained CNN for extracts features from genuine and forged signatures, and three widely used classification algorithms, SVM (Support Vector Machine), NB (Naive Bayes) and KNN (k-nearest neighbors), these algorithms are compared to calculate the run time, classification error, classification loss, and accuracy for test-set consist of signature images (genuine and forgery). Three classifiers have been applied using (UTSig) dataset; where run time, classification error, classification loss and accuracy were calculated for each classifier in the verification phase, the results showed that the SVM and KNN got the best accuracy (76.21), while the SVM got the best run time (0.13) result among other classifiers, therefore the SVM classifier got the best result among the other classifiers in terms of our measures.
OFFLINE SIGNATURE VERIFICATION SYSTEM FOR BANK CHEQUES USING ZERNIKE MOMENTS,...ijaia
Handwritten signature is the most accepted and economical means of personnel authentication. It can be
verified using online or offline schemes. This paper proposes a signature verification model by combining
Zernike moments feature with circularity and aspect ratio. Unlike characters, signatures vary each time
because of its behavioural biometric property. Signatures can be identified based on their shape. Moments
are the good translational and scale invariant shape descriptors. The amplitude and the phase of Zernike
moments, circularity and aspect ratio of the signature are the features that are extracted and combined for
the verification purpose and are fed to the Feedforward Backpropagation Neural Network. This Neural
Network classifies the signature into genuine or forged. Experimental results reveal that this methodology
of combining zernike moments along with the two mentioned geometrical properties give higher accuracy
than using them individually. The combination of these feature vector yields a mean accuracy of 95.83%.
When this approach is compared with the literature, it proves to be more effective.
Offline Signature Verification Using Local Radon Transform and Support Vector...CSCJournals
In this paper, we propose a new method for signature verification using local Radon Transform. The proposed method uses Radon Transform locally as feature extractor and Support Vector Machine (SVM) as classifier. The main idea of our method is using Radon Transform locally for line segments detection and feature extraction, against using it globally. The advantages of the proposed method are robustness to noise, size invariance and shift invariance. Having used a dataset of 600 signatures from 20 Persian writers, and another dataset of 924 signatures from 22 English writers, our system achieves good results. The experimental results of our method are compared with two other methods. This comparison shows that our method has good performance for signature identification and verification in different cultures.
ARABIC ONLINE HANDWRITING RECOGNITION USING NEURAL NETWORKijaia
This article presents the development of an Arabic online handwriting recognition system. To develop our
system, we have chosen the neural network approach. It offers solutions for most of the difficulties linked
to Arabic script recognition. We test the approach with our collected databases. This system shows a good
result and it has a high accuracy (98.50% for characters, 96.90% for words).
Handwritten Character Recognition: A Comprehensive Review on Geometrical Anal...iosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
An Efficient Fingerprint Identification using Neural Network and BAT Algorithm IJECEIAES
The uniqueness, firmness, public recognition, and its minimum risk of intrusion made fingerprint is an expansively used personal authentication metrics. Fingerprint technology is a biometric technique used to distinguish persons based on their physical traits. Fingerprint based authentication schemes are becoming increasingly common and usage of these in fingerprint security schemes, made an objective to the attackers. The repute of the fingerprint image controls the sturdiness of a fingerprint authentication system. We intend for an effective method for fingerprint classification with the help of soft computing methods. The proposed classification scheme is classified into three phases. The first phase is preprocessing in which the fingerprint images are enhanced by employing median filters. After noise removal histogram equalization is achieved for augmenting the images. The second stage is the feature Extraction phase in which numerous image features such as Area, SURF, holo entropy, and SIFT features are extracted. The final phase is classification using hybrid Neural for classification of fingerprint as fake or original. The neural network is unified with BAT algorithm for optimizing the weight factor.
Handwritten character recognition is one of the most challenging and ongoing areas of research in the
field of pattern recognition. HCR research is matured for foreign languages like Chinese and Japanese but
the problem is much more complex for Indian languages. The problem becomes even more complicated for
South Indian languages due to its large character set and the presence of vowels modifiers and compound
characters. This paper provides an overview of important contributions and advances in offline as well as
online handwritten character recognition of Malayalam scripts.
Automatic signature verification with chain code using weighted distance and ...eSAT Journals
Abstract The signature forgery can be restricted by either online or offline signature verification techniques. It verifies the signature by
performing a match with the pre-processed signature dynamically by detecting the motion of stylus during signature while on
other hand, offline verifies by performing a match using the two dimensional scanned image of the signature. This paper studies
about the various techniques available in offline signature verification along with their shadows.
Keywords: Signature Verification, Weighted Distance, High Pressure Factor, Normalization, Threshold Value
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Study of Local Binary Pattern for Partial Fingerprint IdentificationIJMER
Fingerprints are usually used in recognition of a person's identity because of its uniqueness,
stability. Today also the matching of incomplete or partial fingerprints remains challenge. The current
technology is somewhat mature for matching ten prints, but matching of partial fingerprints still needs
a lot of improvement. Automatic fingerprint identification techniques have been successfully adapted to
both civilian and forensic applications. But this Fingerprint identification system suffers from the
problem of handling incomplete prints and discards any partial fingerprints obtained. Level 2 features
are very efficient if the quality of achievement decreases the number of level 2 features will not be
enough for establishing high accuracy in identification. In such cases pores (level 3 features) can be
used for partial fingerprint matching with the help of suitable technique local binary pattern features.
Local binary pattern feature is used to match the pore against with full fingerprints. The first step
involves extracting the pores from the partial image. These pores act as anchor points and sub window
(32*32) is formed surrounding the pores. Then rotation invariant LBP histograms are obtained from
the surrounding window. Finally chi-square formula is used to calculate the minimum distance between
two histograms to find best matching score
ENHANCED SIGNATURE VERIFICATION AND RECOGNITION USING MATLABAM Publications
Signature verification and recognition is a technology that can improve security in our day to day
transaction held in society. This paper presents a novel approach for offline signature verification. In this paper
offline signature verification using neural network is projected, where the signature is written on a paper are
obtained using a scanner or a camera captured and presented in an image format. For authentication of
signature, the proposed method is based on geometrical and statistical feature extraction and then the entire
database, features are trained using neural network .The extracted features of investigation signature are
compared with the previously trained features of the reference signature. This technique is suitable for various
applications such as bank transactions, passports with good authentication results etc
IDENTIFICATION OF SUITED QUALITY METRICS FOR NATURAL AND MEDICAL IMAGESsipij
To assess quality of the denoised image is one of the important task in image denoising application.
Numerous quality metrics are proposed by researchers with their particular characteristics till today. In
practice, image acquisition system is different for natural and medical images. Hence noise introduced in
these images is also different in nature. Considering this fact, authors in this paper tried to identify the
suited quality metrics for Gaussian, speckle and Poisson corrupted natural, ultrasound and X-ray images
respectively. In this paper, sixteen different quality metrics from full reference category are evaluated with
respect to noise variance and suited quality metric for particular type of noise is identified. Strong need to
develop noise dependent quality metric is also identified in this work.
Parallax Effect Free Mosaicing of Underwater Video Sequence Based on Texture ...sipij
In this paper, we present feature-based technique for construction of mosaic image from underwater video
sequence, which suffers from parallax distortion due to propagation properties of light in the underwater
environment. The most of the available mosaic tools and underwater image mosaicing techniques yields
final result with some artifacts such as blurring, ghosting and seam due to presence of parallax in the input
images. The removal of parallax from input images may not reduce its effects instead it must be corrected
in successive steps of mosaicing. Thus, our approach minimizes the parallax effects by adopting an efficient
local alignment technique after global registration. We extract texture features using Centre Symmetric
Local Binary Pattern (CS-LBP) descriptor in order to find feature correspondences, which are used further
for estimation of homography through RANSAC. In order to increase the accuracy of global registration,
we perform preprocessing such as colour alignment between two selected frames based on colour
distribution adjustment. Because of existence of 100% overlap in consecutive frames of underwater video,
we select frames with minimum overlap based on mutual offset in order to reduce the computation cost
during mosaicing. Our approach minimizes the parallax effects considerably in final mosaic constructed
using our own underwater video sequences.
Freeman Chain Code (FCC) Representation in Signature Fraud Detection Based On...CSCJournals
This paper presents a signature verification system that used Freeman Chain Code (FCC) as directional feature and data representation. There are 47 features were extracted from the signature images from six global features. Before extracting the features, the raw images were undergoing pre-processing stages which were binarization, noise removal by using media filter, cropping and thinning to produce Thinned Binary Image (TBI). Euclidean distance is measured and matched between nearest neighbours to find the result. MCYT-SignatureOff-75 database was used. Based on our experiment, the lowest FRR achieved is 6.67% and lowest FAR is 12.44% with only 1.12 second computational time from nearest neighbour classifier. The results are compared with Artificial Neural Network (ANN) classifier.
An appraisal of offline signature verification techniquesSalam Shah
Biometrics is being commonly used nowadays for the identification and verification of humans everywhere in the world. In biometrics humans unique characteristics like palm, fingerprints, iris etc. are being used. Pattern Recognition and image processing are the major areas where research on signature verification is carried out. Hand written Signature of an individual is also unique and for identification of humans are being used and accepted specially in the banking and other financial transactions. The hand written signatures due to its importance are at target of fraudulence. In this paper we have surveyed different papers on techniques that are currently used for the identification and verification of Offline signatures.
Fraud Detection Using Signature RecognitionTejraj Thakor
The signature of person is an important bio metric of a human being which can be used to authenticate human identity. The problem arises when someone decide to imitate our signature and steal our identity.
The Image of human signature is collected by camera of mobile phone which can extract dynamic and spatial information of the signature based on Image processing techniques like Convert to gray scale, Noise Removal, Normalization, Border Elimination and Feature Extraction techniques.
The signature matching is depending on SVM. The SVM classifier is trained with sample images in database obtained from those individuals whose signatures have to be authenticated by the system. In our proposed system SQLite database as a back-end and Android platform as a front-end.
OFFLINE SIGNATURE RECOGNITION VIA CONVOLUTIONAL NEURAL NETWORK AND MULTIPLE C...IJNSA Journal
One of the most important processes used by companies to safeguard the security of information and prevent it from unauthorized access or penetration is the signature process. As businesses and individuals move into the digital age, a computerized system that can discern between genuine and faked signatures is crucial for protecting people's authorization and determining what permissions they have. In this paper, we used Pre-Trained CNN for extracts features from genuine and forged signatures, and three widely used classification algorithms, SVM (Support Vector Machine), NB (Naive Bayes) and KNN (k-nearest neighbors), these algorithms are compared to calculate the run time, classification error, classification loss, and accuracy for test-set consist of signature images (genuine and forgery). Three classifiers have been applied using (UTSig) dataset; where run time, classification error, classification loss and accuracy were calculated for each classifier in the verification phase, the results showed that the SVM and KNN got the best accuracy (76.21), while the SVM got the best run time (0.13) result among other classifiers, therefore the SVM classifier got the best result among the other classifiers in terms of our measures.
OFFLINE SIGNATURE VERIFICATION SYSTEM FOR BANK CHEQUES USING ZERNIKE MOMENTS,...ijaia
Handwritten signature is the most accepted and economical means of personnel authentication. It can be
verified using online or offline schemes. This paper proposes a signature verification model by combining
Zernike moments feature with circularity and aspect ratio. Unlike characters, signatures vary each time
because of its behavioural biometric property. Signatures can be identified based on their shape. Moments
are the good translational and scale invariant shape descriptors. The amplitude and the phase of Zernike
moments, circularity and aspect ratio of the signature are the features that are extracted and combined for
the verification purpose and are fed to the Feedforward Backpropagation Neural Network. This Neural
Network classifies the signature into genuine or forged. Experimental results reveal that this methodology
of combining zernike moments along with the two mentioned geometrical properties give higher accuracy
than using them individually. The combination of these feature vector yields a mean accuracy of 95.83%.
When this approach is compared with the literature, it proves to be more effective.
Offline Signature Verification Using Local Radon Transform and Support Vector...CSCJournals
In this paper, we propose a new method for signature verification using local Radon Transform. The proposed method uses Radon Transform locally as feature extractor and Support Vector Machine (SVM) as classifier. The main idea of our method is using Radon Transform locally for line segments detection and feature extraction, against using it globally. The advantages of the proposed method are robustness to noise, size invariance and shift invariance. Having used a dataset of 600 signatures from 20 Persian writers, and another dataset of 924 signatures from 22 English writers, our system achieves good results. The experimental results of our method are compared with two other methods. This comparison shows that our method has good performance for signature identification and verification in different cultures.
ARABIC ONLINE HANDWRITING RECOGNITION USING NEURAL NETWORKijaia
This article presents the development of an Arabic online handwriting recognition system. To develop our
system, we have chosen the neural network approach. It offers solutions for most of the difficulties linked
to Arabic script recognition. We test the approach with our collected databases. This system shows a good
result and it has a high accuracy (98.50% for characters, 96.90% for words).
Handwritten Character Recognition: A Comprehensive Review on Geometrical Anal...iosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
An Efficient Fingerprint Identification using Neural Network and BAT Algorithm IJECEIAES
The uniqueness, firmness, public recognition, and its minimum risk of intrusion made fingerprint is an expansively used personal authentication metrics. Fingerprint technology is a biometric technique used to distinguish persons based on their physical traits. Fingerprint based authentication schemes are becoming increasingly common and usage of these in fingerprint security schemes, made an objective to the attackers. The repute of the fingerprint image controls the sturdiness of a fingerprint authentication system. We intend for an effective method for fingerprint classification with the help of soft computing methods. The proposed classification scheme is classified into three phases. The first phase is preprocessing in which the fingerprint images are enhanced by employing median filters. After noise removal histogram equalization is achieved for augmenting the images. The second stage is the feature Extraction phase in which numerous image features such as Area, SURF, holo entropy, and SIFT features are extracted. The final phase is classification using hybrid Neural for classification of fingerprint as fake or original. The neural network is unified with BAT algorithm for optimizing the weight factor.
Handwritten character recognition is one of the most challenging and ongoing areas of research in the
field of pattern recognition. HCR research is matured for foreign languages like Chinese and Japanese but
the problem is much more complex for Indian languages. The problem becomes even more complicated for
South Indian languages due to its large character set and the presence of vowels modifiers and compound
characters. This paper provides an overview of important contributions and advances in offline as well as
online handwritten character recognition of Malayalam scripts.
Automatic signature verification with chain code using weighted distance and ...eSAT Journals
Abstract The signature forgery can be restricted by either online or offline signature verification techniques. It verifies the signature by
performing a match with the pre-processed signature dynamically by detecting the motion of stylus during signature while on
other hand, offline verifies by performing a match using the two dimensional scanned image of the signature. This paper studies
about the various techniques available in offline signature verification along with their shadows.
Keywords: Signature Verification, Weighted Distance, High Pressure Factor, Normalization, Threshold Value
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Study of Local Binary Pattern for Partial Fingerprint IdentificationIJMER
Fingerprints are usually used in recognition of a person's identity because of its uniqueness,
stability. Today also the matching of incomplete or partial fingerprints remains challenge. The current
technology is somewhat mature for matching ten prints, but matching of partial fingerprints still needs
a lot of improvement. Automatic fingerprint identification techniques have been successfully adapted to
both civilian and forensic applications. But this Fingerprint identification system suffers from the
problem of handling incomplete prints and discards any partial fingerprints obtained. Level 2 features
are very efficient if the quality of achievement decreases the number of level 2 features will not be
enough for establishing high accuracy in identification. In such cases pores (level 3 features) can be
used for partial fingerprint matching with the help of suitable technique local binary pattern features.
Local binary pattern feature is used to match the pore against with full fingerprints. The first step
involves extracting the pores from the partial image. These pores act as anchor points and sub window
(32*32) is formed surrounding the pores. Then rotation invariant LBP histograms are obtained from
the surrounding window. Finally chi-square formula is used to calculate the minimum distance between
two histograms to find best matching score
ENHANCED SIGNATURE VERIFICATION AND RECOGNITION USING MATLABAM Publications
Signature verification and recognition is a technology that can improve security in our day to day
transaction held in society. This paper presents a novel approach for offline signature verification. In this paper
offline signature verification using neural network is projected, where the signature is written on a paper are
obtained using a scanner or a camera captured and presented in an image format. For authentication of
signature, the proposed method is based on geometrical and statistical feature extraction and then the entire
database, features are trained using neural network .The extracted features of investigation signature are
compared with the previously trained features of the reference signature. This technique is suitable for various
applications such as bank transactions, passports with good authentication results etc
IDENTIFICATION OF SUITED QUALITY METRICS FOR NATURAL AND MEDICAL IMAGESsipij
To assess quality of the denoised image is one of the important task in image denoising application.
Numerous quality metrics are proposed by researchers with their particular characteristics till today. In
practice, image acquisition system is different for natural and medical images. Hence noise introduced in
these images is also different in nature. Considering this fact, authors in this paper tried to identify the
suited quality metrics for Gaussian, speckle and Poisson corrupted natural, ultrasound and X-ray images
respectively. In this paper, sixteen different quality metrics from full reference category are evaluated with
respect to noise variance and suited quality metric for particular type of noise is identified. Strong need to
develop noise dependent quality metric is also identified in this work.
Parallax Effect Free Mosaicing of Underwater Video Sequence Based on Texture ...sipij
In this paper, we present feature-based technique for construction of mosaic image from underwater video
sequence, which suffers from parallax distortion due to propagation properties of light in the underwater
environment. The most of the available mosaic tools and underwater image mosaicing techniques yields
final result with some artifacts such as blurring, ghosting and seam due to presence of parallax in the input
images. The removal of parallax from input images may not reduce its effects instead it must be corrected
in successive steps of mosaicing. Thus, our approach minimizes the parallax effects by adopting an efficient
local alignment technique after global registration. We extract texture features using Centre Symmetric
Local Binary Pattern (CS-LBP) descriptor in order to find feature correspondences, which are used further
for estimation of homography through RANSAC. In order to increase the accuracy of global registration,
we perform preprocessing such as colour alignment between two selected frames based on colour
distribution adjustment. Because of existence of 100% overlap in consecutive frames of underwater video,
we select frames with minimum overlap based on mutual offset in order to reduce the computation cost
during mosaicing. Our approach minimizes the parallax effects considerably in final mosaic constructed
using our own underwater video sequences.
Contrast enhancement using various statistical operations and neighborhood pr...sipij
Histogram Equalization is a simple and effective contrast enhancement technique. In spite of its popularity
Histogram Equalization still have some limitations –produces artifacts, unnatural images and the local
details are not considered, therefore due to these limitations many other Equalization techniques have been
derived from it with some up gradation. In this proposed method statistics play an important role in image
processing, where statistical operations is applied to the image to get the desired result such as
manipulation of brightness and contrast. Thus, a novel algorithm using statistical operations and
neighborhood processing has been proposed in this paper where the algorithm has proven to be effective in
contrast enhancement based on the theory and experiment.
Image retrieval and re ranking techniques - a surveysipij
There is a huge amount of research work focusing on the searching, retrieval and re-ranking of images in
the image database. The diverse and scattered work in this domain needs to be collected and organized for
easy and quick reference.
Relating to the above context, this paper gives a brief overview of various image retrieval and re-ranking
techniques. Starting with the introduction to existing system the paper proceeds through the core
architecture of image harvesting and retrieval system to the different Re-ranking techniques. These
techniques are discussed in terms of approaches, methodologies and findings and are listed in tabular form
for quick review.
A combined method of fractal and glcm features for mri and ct scan images cla...sipij
Fractal analysis has been shown to be useful in image processing for characterizing shape and gray-scale
complexity. The fractal feature is a compact descriptor used to give a numerical measure of the degree of
irregularity of the medical images. This descriptor property does not give ownership of the local image
structure. In this paper, we present a combination of this parameter based on Box Counting with GLCM
Features. This powerful combination has proved good results especially in classification of medical texture
from MRI and CT Scan images of trabecular bone. This method has the potential to improve clinical
diagnostics tests for osteoporosis pathologies.
Speaker Identification From Youtube Obtained Datasipij
An efficient, and intuitive algorithm is presented for the identification of speakers from a long dataset (like
YouTube long discussion, Cocktail party recorded audio or video).The goal of automatic speaker
identification is to identify the number of different speakers and prepare a model for that speaker by
extraction, characterization and speaker-specific information contained in the speech signal. It has many
diverse application specially in the field of Surveillance , Immigrations at Airport , cyber security ,
transcription in multi-source of similar sound source, where it is difficult to assign transcription arbitrary.
The most commonly speech parameterization used in speaker verification, K-mean, cepstral analysis, is
detailed. Gaussian mixture modeling, which is the speaker modeling technique is then explained. Gaussian
mixture models (GMM), perhaps the most robust machine learning algorithm has been introduced to
examine and judge carefully speaker identification in text independent. The application or employment of
Gaussian mixture models for monitoring & Analysing speaker identity is encouraged by the familiarity,
awareness, or understanding gained through experience that Gaussian spectrum depict the characteristics
of speaker's spectral conformational pattern and remarkable ability of GMM to construct capricious
densities after that we illustrate 'Expectation maximization' an iterative algorithm which takes some
arbitrary value in initial estimation and carry on the iterative process until the convergence of value is
observed We have tried to obtained 85 ~ 95% of accuracy using speaker modeling of vector quantization
and Gaussian Mixture model ,so by doing various number of experiments we are able to obtain 79 ~ 82%
of identification rate using Vector quantization and 85 ~ 92.6% of identification rate using GMM modeling
by Expectation maximization parameter estimation depending on variation of parameter.
Robust content based watermarking algorithm using singular value decompositio...sipij
Nowadays, image content is frequently subject to different malicious manipulations. To protect images
from this illegal manipulations computer science community have recourse to watermarking techniques. To
protect digital multimedia content we need just to embed an invisible watermark into images which
facilitate the detection of different manipulations, duplication, illegitimate distributions of these images. In
this work a robust watermarking technique is presented that embedding invisible watermarks into colour
images the singular value decomposition bloc by bloc of a robust transform of images that is the Radial
symmetry transform. Each bit of the watermark is inserted in a bloc of eight pixels large of the blue
channel a high singular value of the corresponding bloc into the radial symmetry map. We justified the
insertion in the blue channel by our feeble sensibility to perturbations in this colour channel of images. We
present also results obtained with different tests. We had tested the imperceptibility of the mark using this
approach and also its robustness face to several attacks.
Lossless image compression using new biorthogonal waveletssipij
Even though a large number of wavelets exist, one needs new wavelets for their specific applications. One
of the basic wavelet categories is orthogonal wavelets. But it was hard to find orthogonal and symmetric
wavelets. Symmetricity is required for perfect reconstruction. Hence, a need for orthogonal and symmetric
arises. The solution was in the form of biorthogonal wavelets which preserves perfect reconstruction
condition. Though a number of biorthogonal wavelets are proposed in the literature, in this paper four new
biorthogonal wavelets are proposed which gives better compression performance. The new wavelets are
compared with traditional wavelets by using the design metrics Peak Signal to Noise Ratio (PSNR) and
Compression Ratio (CR). Set Partitioning in Hierarchical Trees (SPIHT) coding algorithm was utilized to
incorporate compression of images.
Global threshold and region based active contour model for accurate image seg...sipij
In this contribution, we develop a novel global threshold-based active contour model. This model deploys a new
edge-stopping function to control the direction of the evolution and to stop the evolving contour at weak or
blurred edges. An implementation of the model requires the use of selective binary and Gaussian filtering
regularized level set (SBGFRLS) method. The method uses either a selective local or global segmentation
property. It penalizes the level set function to force it to become a binary function. This procedure is followed by
using a regularisation Gaussian. The Gaussian filters smooth the level set function and stabilises the evolution
process. One of the merits of our proposed model stems from the ability to initialise the contour anywhere inside
the image to extract object boundaries. The proposed method is found to perform well, notably when the
intensities inside and outside the object are homogenous. Our method is applied with satisfactory results on
various types of images, including synthetic, medical and Arabic-characters images.
Beamforming with per antenna power constraint and transmit antenna selection ...sipij
In this paper, transmit beamforming and antenna selection techniques are presented for the Cooperative
Distributed Antenna System. Beamforming technique with minimum total weighted transmit power
satisfying threshold SINR and Per-Antenna Power constraints is formulated as a convex optimization
problem for the efficient performance of Distributed Antenna System (DAS). Antenna Selection technique is
implemented in this paper to select the optimum Remote Antenna Units from all the available ones. This
achieves the best compromise between capacity and system complexity. Dual polarized and Triple
Polarized systems are considered. Simulation results prove that by integrating Beamforming with DAS
enhances its performance. Also by using convex optimization in Antenna Selection enhances the
performance of multi polarized systems.
A Novel Uncertainty Parameter SR ( Signal to Residual Spectrum Ratio ) Evalua...sipij
Usually, hearing impaired people use hearing aids which are implemented with speech enhancement
algorithms. Estimation of speech and estimation of nose are the components in single channel speech
enhancement system. The main objective of any speech enhancement algorithm is estimation of noise power
spectrum for non stationary environment. VAD (Voice Activity Detector) is used to identify speech pauses
and during these pauses only estimation of noise. MMSE (Minimum Mean Square Error) speech
enhancement algorithm did not enhance the intelligibility, quality and listener fatigues are the perceptual
aspects of speech. Novel evaluation approach SR (Signal to Residual spectrum ratio) based on uncertainty
parameter introduced for the benefits of hearing impaired people in non stationary environments to control
distortions. By estimation and updating of noise based on division of original pure signal into three parts
such as pure speech, quasi speech and non speech frames based on multiple threshold conditions. Different
values of SR and LLR demonstrate the amount of attenuation and amplification distortions. The proposed
method will compared with any one method WAT(Weighted Average Technique) Hence by using
parameters SR (signal to residual spectrum ratio) and LLR (log like hood ratio), MMSE (Minim Mean
Square Error) in terms of segmented SNR and LLR.
A voting based approach to detect recursive order number of photocopy documen...sipij
Photocopy documents are very common in our normal life. People are permitted to carry and present
photocopied documents to avoid damages to the original documents. But this provision is misused for
temporary benefits by fabricating fake photocopied documents. Fabrication of fake photocopied document
is possible only in 2nd and higher order recursive order of photocopies. Whenever a photocopied document
is submitted, it may be required to check its originality. When the document is 1st order photocopy, chances
of fabrication may be ignored. On the other hand when the photocopy order is 2nd or above, probability of
fabrication may be suspected. Hence when a photocopy document is presented, the recursive order number
of photocopy is to be estimated to ascertain the originality. This requirement demands to investigate
methods to estimate order number of photocopy. In this work, a voting based approach is used to detect the
recursive order number of the photocopy document using probability distributions exponential, extreme
values and lognormal distributions is proposed. A detailed experimentation is performed on a generated
data set and the method exhibits efficiency close to 89%.
An intensity based medical image registration using genetic algorithmsipij
Medical imaging plays a vital role to create images of human body for clinical purposes. Biomedical
imaging has taken a leap by entering into the field of image registration. Image registration integrates the
large amount of medical information embedded in the images taken at different time intervals and images
at different orientations. In this paper, an intensity-based real-coded genetic algorithm is used for
registering two MRI images. To demonstrate the efficiency of the algorithm developed, the alignment of the
image is altered and algorithm is tested for better performance. Also the work involves the comparison of
two similarity metrics, and based on the outcome the best metric suited for genetic algorithm is studied.
Feature selection approach in animal classificationsipij
In this paper, we propose a model for automatic classification of Animals using different classifiers Nearest
Neighbour, Probabilistic Neural Network and Symbolic. Animal images are segmented using maximal
region merging segmentation. The Gabor features are extracted from segmented animal images.
Discriminative texture features are then selected using the different feature selection algorithm like
Sequential Forward Selection, Sequential Floating Forward Selection, Sequential Backward Selection and
Sequential Floating Backward Selection. To corroborate the efficacy of the proposed method, an
experiment was conducted on our own data set of 25 classes of animals, containing 2500 samples. The
data set has different animal species with similar appearance (small inter-class variations) across different
classes and varying appearance (large intra-class variations) within a class. In addition, the images of
flowers are of different poses, with cluttered background under different lighting and climatic conditions.
Experiment results reveal that Symbolic classifier outperforms Nearest Neighbour and Probabilistic Neural
Network classifiers.
Review of ocr techniques used in automatic mail sorting of postal envelopessipij
This paper presents a review of various OCR techniq
ues used in the automatic mail sorting process. A
complete description on various existing methods fo
r address block extraction and digit recognition th
at
were used in the literature is discussed. The objec
tive of this study is to provide a complete overvie
w about
the methods and techniques used by many researchers
for automating the mail sorting process in postal
service in various countries. The significance of Z
ip code or Pincode recognition is discussed.
Application of parallel algorithm approach for performance optimization of oi...sipij
This paper gives a detailed study on the performance of image filter algorithm with various parameters
applied on an image of RGB model. There are various popular image filters, which consumes large amount
of computing resources for processing. Oil paint image filter is one of the very interesting filters, which is
very performance hungry. Current research tries to find improvement in oil paint image filter algorithm by
using parallel pattern library. With increasing kernel-size, the processing time of oil paint image filter
algorithm increases exponentially. I have also observed in various blogs and forums, the questions for
faster oil paint have been asked repeatedly.
Highly Secured Bio-Metric Authentication Model with Palm Print IdentificationIJERA Editor
For securing personal identifications and highly secure identification problems, biometric technologies will
provide higher security with improved accuracy. This has become an emerging technology in recent years due to
the transaction frauds, security breaches and personal identification etc. The beauty of biometric technology is it
provides a unique code for each person and it can’t be copied or forged by others. To overcome the draw backs
of finger print identification systems, here in this paper we proposed a palm print based personal identification
system, which is a most promising and emerging research area in biometric identification systems due to its
uniqueness, scalability, faster execution speed and large area for extracting the features. It provides higher
security over finger print biometric systems with its rich features like wrinkles, continuous ridges, principal
lines, minutiae points, and singular points. The main aim of proposed palm print identification system is to
implement a system with higher accuracy and increased speed in identifying the palm prints of several users.
Here, in this we presented a highly secured palm print identification system with extraction of region of interest
(ROI) with morphological operation there by applying un-decimated bi-orthogonal wavelet (UDBW) transform
to extract the low level features of registered palm prints to calculate its feature vectors (FV) then after the
comparison is done by measuring the distance between registered palm feature vector and testing palm print
feature vector. Simulation results show that the proposed biometric identification system provides more
accuracy and reliable recognition rate
Signature verification based on proposed fast hyper deep neural networkIAESIJAI
Many industries have made widespread use of the handwittern signature verification system, including banking, education, legal proceedings, and criminal investigation, in which verification and identification are absolutely necessary. In this research, we have developed an accurate offline signature verification model that can be used in a writer-independent scenario. First, the handwitten signature images went through four preprocessing stages in order to be suitable for finding the unique features. Then, three different types of features namely principal component analysis (PCA) as appearance-based features, gray-level co-occurrence matrix (GLCM) as texture-features, and fast Fourier transform (FFT) as frequency-features are extracted from signature images in order to build a hybrid feature vector for each image. Finally, to classify signature features, we have designed a proposed fast hyper deep neural network (FHDNN) architecture. Two different datasets are used to evaluate our model these are SigComp2011, and CEDAR datasets. The results collected demonstrate that the suggested model can operate with accuracy equal to 100%, outperforming several of its predecessors. In the terms of (precision, recall, and F-score) it gives a very good results for both datasets and exceeds (1.00, 0.487, and 0.655 respectively) on Sigcomp2011 dataset and (1.00, 0.507, and 0.672 respectively) on CEDAR dataset.
The human signature provides a natural and publically-accepted legally-admissible method for providing authentication to a process. Automatic biometric signature systems assess both the drawn image and the temporal aspects of signature construction, providing enhanced verification rates over and above conventional outcome assessment. To enable the capture of these constructional data requires the use of specialist ‘tablet’ devices. In this paper we explore the enrolment performance using a range of common signature capture devices and investigate the reasons behind user preference. The results show that writing feedback and familiarity with conventional ‘paper and pen’ donation configurations are the primary motivation for user preference. These results inform the choice of signature device from both technical performance and user acceptance viewpoints.
Mobile User Authentication Based On User Behavioral Pattern (MOUBE)CSCJournals
Smart devices are equipped with multiple authentication techniques and still remain prone to
attacks since all of these techniques require explicit user intervention. The purpose of this paper
is to capture the user behavior in order to use it as an implicit authentication technique.
In this paper, we introduce a novel authentication model to be used complementary to the
existing models; Particularly, the context of the user, the duration of usage of each application
and the occurrence time were examined and modeled using the cubic spline function as an
authentication technique. A software system composed of two software components has been
implemented on Android platform. Preliminary results show a 76% accuracy rate in determining
the rightful owner of the device.
LUIS: A L IGHT W EIGHT U SER I DENTIFICATION S CHEME FOR S MARTPHONES IJCI JOURNAL
Smartphone usage has reached its peak. There has be
en a tremendous growth in the number of people
migrating from PCs to smart phones. Numerous scenar
ios such as loss of a phone, phone theft etc., can
lead to unauthorized use of one’s own smartphone. T
his raises the concern for securing personal and
private data. This project proposes a light weight
two level user identification scheme to recognize a
nd
authenticate the mobile phone based on the device h
olding and usage patterns. To validate the proposed
scheme, an application is created which takes a ges
ture input characterized by time of swiping the scr
een,
finger pressure, phone movements and location of sw
ipe on the screen through X and Y co-ordinate. A
threshold based matching scheme performs classifica
tion to find the true owner. Results show that the
scheme was able to achieve 90% true positives and 1
0% false positives with a 0.5% of battery usage.
A Novel Automated Approach for Offline Signature Verification Based on Shape ...Editor IJCATR
The handwritten signature has been the most natural and long lasting authentication scheme in which a person draw some
pattern of lines or writes his name in a different style. The signature recognition and verification are a behavioural biometric and is
very challenging due to the variation that can occur in person’s signature because of age, illness, and emotional state of the person. As
far as the representation of the signature is concerned a classical technique of thinning or skeleton is mostly used. In this paper, we
proposed a new methodology for signature verification that uses structural information and original strokes instead of skeleton or
thinned version to analyse the signature and verify. The approach is based on sketching a fixed size grid over the signatures and getting
2-Dimensional unique templates which are then compared and matched to verify a query signature as genuine or forged. To compute
the similarity score between two signature’s grids, we follow template matching rule and the Signature grid’s cell are mapped and
matched with respect to position. The proposed framework is fast and highly accurate with reduce false acceptance rate and false
In this paper we design a system which takes student attendance and the attendance records are maintained
automatically in an academic institute. Taking the attendance manually and maintaining its record till end
of year (or even beyond) is very difficult job as well as wastage of time and paper. This necessitates an
efficient system that would be fully automatic. Top level design of the system includes marking attendance
with the help of a finger-print sensor module and saving the records to a computer or server. Fingerprint sensor module and LCD screen are portable although they can also be fixed to a location for e.g. entry/ exit points. To begin with, a student needs to be registered in the finger-print sensor module. Thereafter every time the student attends a lecture he/ she will place his/her finger on the fingerprint sensor module. The
finger-print sensor module will update the attendance record in database. The student can see the notification on LCD screen.
Data security and privacy are crucial issues to be addressed for assuring a successful deployment of biometrics-based recognition systems in real life applications. In this paper, we present a highly efficient and secured authentication scheme by online verification of signature. This authentication scheme is very simple and can be used for securing the applications and various elements which can be accessed and interfaced by touch panel’s inputs. This authentication scheme is very simple and can be used for securing the applications and various elements which can be accessed and interfaced by touch panel’s inputs.
DevOps and Testing slides at DASA ConnectKari Kakkonen
My and Rik Marselis slides at 30.5.2024 DASA Connect conference. We discuss about what is testing, then what is agile testing and finally what is Testing in DevOps. Finally we had lovely workshop with the participants trying to find out different ways to think about quality and testing in different parts of the DevOps infinity loop.
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Ramesh Iyer
In today's fast-changing business world, Companies that adapt and embrace new ideas often need help to keep up with the competition. However, fostering a culture of innovation takes much work. It takes vision, leadership and willingness to take risks in the right proportion. Sachin Dev Duggal, co-founder of Builder.ai, has perfected the art of this balance, creating a company culture where creativity and growth are nurtured at each stage.
State of ICS and IoT Cyber Threat Landscape Report 2024 previewPrayukth K V
The IoT and OT threat landscape report has been prepared by the Threat Research Team at Sectrio using data from Sectrio, cyber threat intelligence farming facilities spread across over 85 cities around the world. In addition, Sectrio also runs AI-based advanced threat and payload engagement facilities that serve as sinks to attract and engage sophisticated threat actors, and newer malware including new variants and latent threats that are at an earlier stage of development.
The latest edition of the OT/ICS and IoT security Threat Landscape Report 2024 also covers:
State of global ICS asset and network exposure
Sectoral targets and attacks as well as the cost of ransom
Global APT activity, AI usage, actor and tactic profiles, and implications
Rise in volumes of AI-powered cyberattacks
Major cyber events in 2024
Malware and malicious payload trends
Cyberattack types and targets
Vulnerability exploit attempts on CVEs
Attacks on counties – USA
Expansion of bot farms – how, where, and why
In-depth analysis of the cyber threat landscape across North America, South America, Europe, APAC, and the Middle East
Why are attacks on smart factories rising?
Cyber risk predictions
Axis of attacks – Europe
Systemic attacks in the Middle East
Download the full report from here:
https://sectrio.com/resources/ot-threat-landscape-reports/sectrio-releases-ot-ics-and-iot-security-threat-landscape-report-2024/
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Albert Hoitingh
In this session I delve into the encryption technology used in Microsoft 365 and Microsoft Purview. Including the concepts of Customer Key and Double Key Encryption.
Epistemic Interaction - tuning interfaces to provide information for AI supportAlan Dix
Paper presented at SYNERGY workshop at AVI 2024, Genoa, Italy. 3rd June 2024
https://alandix.com/academic/papers/synergy2024-epistemic/
As machine learning integrates deeper into human-computer interactions, the concept of epistemic interaction emerges, aiming to refine these interactions to enhance system adaptability. This approach encourages minor, intentional adjustments in user behaviour to enrich the data available for system learning. This paper introduces epistemic interaction within the context of human-system communication, illustrating how deliberate interaction design can improve system understanding and adaptation. Through concrete examples, we demonstrate the potential of epistemic interaction to significantly advance human-computer interaction by leveraging intuitive human communication strategies to inform system design and functionality, offering a novel pathway for enriching user-system engagements.
Transcript: Selling digital books in 2024: Insights from industry leaders - T...BookNet Canada
The publishing industry has been selling digital audiobooks and ebooks for over a decade and has found its groove. What’s changed? What has stayed the same? Where do we go from here? Join a group of leading sales peers from across the industry for a conversation about the lessons learned since the popularization of digital books, best practices, digital book supply chain management, and more.
Link to video recording: https://bnctechforum.ca/sessions/selling-digital-books-in-2024-insights-from-industry-leaders/
Presented by BookNet Canada on May 28, 2024, with support from the Department of Canadian Heritage.
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Jeffrey Haguewood
Sidekick Solutions uses Bonterra Impact Management (fka Social Solutions Apricot) and automation solutions to integrate data for business workflows.
We believe integration and automation are essential to user experience and the promise of efficient work through technology. Automation is the critical ingredient to realizing that full vision. We develop integration products and services for Bonterra Case Management software to support the deployment of automations for a variety of use cases.
This video focuses on the notifications, alerts, and approval requests using Slack for Bonterra Impact Management. The solutions covered in this webinar can also be deployed for Microsoft Teams.
Interested in deploying notification automations for Bonterra Impact Management? Contact us at sales@sidekicksolutionsllc.com to discuss next steps.
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...UiPathCommunity
💥 Speed, accuracy, and scaling – discover the superpowers of GenAI in action with UiPath Document Understanding and Communications Mining™:
See how to accelerate model training and optimize model performance with active learning
Learn about the latest enhancements to out-of-the-box document processing – with little to no training required
Get an exclusive demo of the new family of UiPath LLMs – GenAI models specialized for processing different types of documents and messages
This is a hands-on session specifically designed for automation developers and AI enthusiasts seeking to enhance their knowledge in leveraging the latest intelligent document processing capabilities offered by UiPath.
Speakers:
👨🏫 Andras Palfi, Senior Product Manager, UiPath
👩🏫 Lenka Dulovicova, Product Program Manager, UiPath
Accelerate your Kubernetes clusters with Varnish CachingThijs Feryn
A presentation about the usage and availability of Varnish on Kubernetes. This talk explores the capabilities of Varnish caching and shows how to use the Varnish Helm chart to deploy it to Kubernetes.
This presentation was delivered at K8SUG Singapore. See https://feryn.eu/presentations/accelerate-your-kubernetes-clusters-with-varnish-caching-k8sug-singapore-28-2024 for more details.
Generating a custom Ruby SDK for your web service or Rails API using Smithyg2nightmarescribd
Have you ever wanted a Ruby client API to communicate with your web service? Smithy is a protocol-agnostic language for defining services and SDKs. Smithy Ruby is an implementation of Smithy that generates a Ruby SDK using a Smithy model. In this talk, we will explore Smithy and Smithy Ruby to learn how to generate custom feature-rich SDKs that can communicate with any web service, such as a Rails JSON API.
Securing your Kubernetes cluster_ a step-by-step guide to success !KatiaHIMEUR1
Today, after several years of existence, an extremely active community and an ultra-dynamic ecosystem, Kubernetes has established itself as the de facto standard in container orchestration. Thanks to a wide range of managed services, it has never been so easy to set up a ready-to-use Kubernetes cluster.
However, this ease of use means that the subject of security in Kubernetes is often left for later, or even neglected. This exposes companies to significant risks.
In this talk, I'll show you step-by-step how to secure your Kubernetes cluster for greater peace of mind and reliability.
From Siloed Products to Connected Ecosystem: Building a Sustainable and Scala...
Offline handwritten signature identification using adaptive window positioning techniques
1. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
DOI : 10.5121/sipij.2014.5302 13
OFFLINE HANDWRITTEN SIGNATURE
IDENTIFICATION USING ADAPTIVE WINDOW
POSITIONING TECHNIQUES
Ghazali Sulong, Anwar Yahy Ebrahim and Muhammad Jehanzeb
UTM-IRDA Digital media centre (MaGIC-X), Faculty of Computing, Universiti
Tecknologi Malaysia (UTM) Skudai 81310, Johor, Malaysia
ABSTRACT
The paper presents to address this challenge, we have proposed the use of Adaptive Window Positioning
technique which focuses on not just the meaning of the handwritten signature but also on the individuality
of the writer. This innovative technique divides the handwritten signature into 13 small windows of size nxn
(13x13). This size should be large enough to contain ample information about the style of the author and
small enough to ensure a good identification performance. The process was tested with a GPDS dataset
containing 4870 signature samples from 90 different writers by comparing the robust features of the test
signature with that of the user’s signature using an appropriate classifier. Experimental results reveal that
adaptive window positioning technique proved to be the efficient and reliable method for accurate
signature feature extraction for the identification of offline handwritten signatures .The contribution of this
technique can be used to detect signatures signed under emotional duress.
KEYWORDS
Offline Handwritten Signature, GPDS dataset, Verification, Identification, Adaptive window positioning.
1. INTRODUCTION
The signature of any person is an important biometric characteristic which is usually implemented
for personnel identification or document authentication. An increasing number of financial and
business transactions are approved via signatures [1]. Handwritten signature as a method of
authentication has become a part of everyday life, and there is probably not a single area where it
is not used. Handwritten signature usage dates from ancient times and is held until today as a
means of giving consent to something that needs to be done. The problem arises when someone
decides to imitate the signature of the person with the purpose of fraud or false representation.
Therefore, there is need for adequate protection personal signatures. One good method of
protection is by the use of biometric systems based on handwritten signature [2].
Handwritten signature is defined as the first and last name written in your own handwriting [3]. It
is often the case that the signature does not contain the full name but only one part of it, or
sometimes a set of connected lines that do not resemble the name of the signer. This type of
signature is called paraph, and is defined as an abbreviated signature, sometimes only the initial
letter of the name, and placed on administrative act within the routine procedure, which means
that whoever put the initials agrees to endorse the content. Work on signature can be carried out
by using either signature identification or signature verification. Signature Identification can be
done using a person's identity based only on biometric measurements. Signature verification is the
2. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
14
process used to recognize an individual’s handwritten signature for genuine or duplicate/forgery
[4]. Signature identification and verification system are broadly classified in two ways: on-line
and off-line. In an off-line technique, signature is signed on a piece of paper and scanned into a
computer system. In an on-line technique, signature is signed on a digitizer and dynamic
information like speed, and pressure is captured in addition to a static image of the signature.
Verification decision is usually based on local or global features extracted from the signature
being processed. Excellent verification results can be achieved by comparing the robust features
of the test signature with that of the user’s signature using an appropriate classifier [5].Due to the
relative ease of use of an offline system, a number of applications worldwide prefer to use this
system (e.g. Check verification in the bank) [6]. Even though the dynamic signature verification
is more reliable as compared to offline systems in terms of accuracy, this online method requires
special hardware digitizers, and pressure sensitivity tablet to capture the dynamic features, which
the offline method does not require [7]. For an offline method, the extracted features of the
individual’s signature consider as an input to the system, which is then processed based on some
predefined standardized methods. After the standardization stage, called pre-processing, extracted
features from the offline handwritten signature are then identified and verified against a stored
data set through a process known as graph matching. However, researchers in this field have
failed to take into account external factors that may influence the signature of an individual as the
individual may be under different emotions when signing his signature [8] [9] [10]. Thus, an
individual though having a unique signature may sign a signature that can be in different shapes
under different situations. Thus, it is important to take into account external factors when
investigating a signature verification technique. This paper therefore attempts to address this
challenge for offline handwritten signature identification by proposing a new technique based
adaptive window positioning method for signature feature extraction that will give reliable
accuracy in verifying an individual’s signature even when the user is under different emotions
since signature verification applications are used in our daily lives and will be exposed to human
emotions. This proposed technique improves the efficiency and accuracy of offline handwritten
signature verification and identification system. It also has a more enriched process of signature
feature extraction by using the adaptive window positioning method. This gives it the ability to
verify and identify an individual’s signature even when signed under emotional stress.
Furthermore, this study creates room for further research into the application of this technique in
offline handwritten signature verification. The paper is organized as follows: Section 2 presents a
review of related work to the study. Section 3 describes our proposed method. Section 4
discusses the results of our experiments using GPDS dataset. Section 5 concludes the paper.
2. BACKGROUND OF THE STUDY
Broadly, features can be classified as global or local, where global features represent signature’s
properties as a whole and local ones correspond to properties specific to a sampling point [11].
There are several feature extraction techniques employed in signature verification and
identification systems [12] [13]. The basic purpose of any feature extraction is to extract accurate
features from any given sample. The amount of feature extracted is irrelevant to the overall
accuracy of the result as fewer features may be extracted using any techniques, and yet yield
better result than one in which a large number of features are extracted. Thus the focus locus is
the technique employed. Global and local features contain information, which are effective for
signature recognition. Selection of different features is vital for any pattern recognition and
classification technique [14]. Global signature features are extracted from the whole signature
image. On the other hand, local geometric features are extracted from signature grids. Moreover,
each grid can be used to extract the same ranges of global features. The Combination of these
global and local features is further used to successfully determine the identity of authentic and
forged signatures from a database. This set of geometric features is
Used as input to the identification system.
3. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
15
Table 1. List Different Offline Handwritten Signature Identification and Verification Methods
S/N Approach Characteristics Advantages Disadvantages
1. Template
Matching
approach
- Employs pattern comparison
process
- Suitable for detecting
genuine signatures via
rigid matching
- Not appropriate
for detecting
skilled forgeries
2. Neural
Networks
(NN)
approach
- Learns by example thus good
for learning the underlying
structure of the data set.
- Can be used to model
complex functions
- Highly suitable for modeling
global features of handwritten
signatures
- Widely accepted
classifiers for pattern
recognition problems
- Has very low FAR and
FRR results
- Not very
suitable for
modeling
statistical and
geometric features
- Requires a
highly
representative
data set
3. Hidden
Markov
Models
(HMM)
approach
- Best suited for sequence
analysis in signature
verification
- Uses stochastic matching
(model and signature) to
extract variability between
patterns and their similarities
- Has various topologies and
adopts probability density
function modeling in its design
for the verification task
- Can easily detect simple
and random forgeries in
signature verification
- Very poor in
detecting skilled
forgery
4. Statistical
approach
- Employs statistical method to
determine the relationship,
deviation, etc between two or
more data items
- Uses the concept of
Correlation Coefficients
- Good at identifying
random and simple
forgeries
Its :graphometry -based
approach avails so many
usable features for
signature verification, e.g.,
calibration, proportion,
guideline and base
behavior
- Its use of static
features limits it
from detecting
skilled forgery
5. Structural
and
Syntactic
approach
- Uses symbolic data (e.g.
Signatures) structures such as
strings, graphs, and trees to
represent recognition patterns
- Employs the use of a
Modified Direction Feature
(MDF) to extract transition
locations
- Appropriate for detecting
genuine signatures and
targeted forged signatures
- Very exhaustive
method as it
requires large
computational
efforts and
training sets
6. Wavelet-
based
approach
- It is a multi-resolution
transform that can decompose
a signal into lowpass and
highpass information
- Wavelet theory is employed
in decomposing a curvature-
based signature into a multi-
resolution signal
- Can be applied in both
offline and online
signature verification
- Can decompose a
curvature-based signature
into a multi-resolution
format
- Can be applied to
symbolic languages such
as Chinese and Japanese
besides English
4. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
16
The global features that are extracted from the signature sample include [13]: Width (Length),
Height, Aspect ratio [15], Horizontal projection, Vertical projection, Area of black pixels,
Normalized area, Center of gravity, Maximum and minimum black pixels in vertical projection,
Maximum and minimum black pixels in horizontal projection, Global baseline, Upper and lower
edge limits, Middle zone, Hough transform [16], Curvelet transform. Local features- also known
as Grid features can be extracted from gray level, binary and thinned signature images. From the
small regions of the whole image, local features are estimated, such as center of gravity, width,
height, horizontal and vertical projections, aspect ratio, area of black pixels of each grid region,
normalized area of black pixels, gradient and concavity features etc . The global features can also
be considered as local features for each grid region. To obtain a set of global and local features,
both of these feature sets are combined into a feature vector and the feature vector is sent as input
to the classifiers for generating matching scores [16] [2]. Other offline signature features include
Statistical features [10], Geometry and topological features [17], Kurtosis [18], Orientation [18],
Gabor Wavelet [19], Eccentricity [18], Skewness [15], Discrete Wavelet Transform (DWT)
Features [20], Modified Direction Feature [15], and Contour let transform (CT) [21] [15].
3. PROPOSED METHOD
In this section, we present our method and its application processes to offline signature feature
extraction using the adaptive window positioning technique. Thus, the section illustrates the
proposed methodology for the offline handwritten signature identification system using adaptive
widow positioning technique. Here, we follow through all the logical steps involved starting from
getting the handwritten offline signature image to the signature identification stages. Figure 1
presents a flowchart of our proposed system.
Figure 1. Flowchart of offline signature identification process using window positioning
technique
5. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
17
3.1. Data Acquisition and Pre Processing
This consists of the data collection and signature image pre-processing stages. Our data was
collected from GPDS dataset because it is one of the well-known and widely used databases in
signature identification and verification applications and researches. GPDS dataset is a
standardized database of offline English signature images containing 4870 signature samples of
90 different writers. The pre-processing stage is responsible for improving the image quality, and
precedes the signature fragmentation phase. It makes extraction and identification of the
individual features much easier by improving the identification performance. Sometimes, some of
the original information is lost during the clean-up process of the background noise of the
digitized image. For the purpose of our study, a global threshold of Otsu’s algorithm was used in
this study to convert the selected dataset images into binary images of the signature. This binary
image serves as input to the next step.
3.2. Signature Image Windowing
In order to extract the writing patterns used frequently by an individual, we first implement
division (segmentation) on the signature to produce small sub-images (fragments). This division
is carried out by positioning small windows over the signature in a way that will exploit most of
the redundancy in the signature and produce signature fragments that allows for meaningful
comparison of these fragments. We have chosen to carry out this division in square windows of
nxn; this size should be large enough to contain ample information about the style of the author
and small enough to ensure a good identification performance. In this paper, the window size that
has been used is fixed at a value of 13 because a window size (13x13) can be applied to any input
image to get the optimum output. This adaptive window positioning method seeks to follow the
ink trace with the objective of achieving an optimal window positioning that is based on the
analysis of the skeleton of the handwritten signature image with respect to the drawing. This is
made possible by removing the pixels on the boundaries of the component without breaking it
apart, then placing the first window on the original component by finding the first image pixel
(the starting point of the written component) and scanning the pixel from top to bottom and left to
right as shown in Figure 2a. The second step is to copy the same placed window on the skeleton
image and define a four-flag direction (East, West, North and South) for each window, and set the
related flag if the skeleton exits from that particular side as shown in Figure 2b.
(a) (b)
Figure 2. (a) Skeleton trace. (b) Window positioning on a component
If the skeleton exits from the E, then the next window must be placed towards the right of the
current window (on the original component) as shown in Figure 3a, and then shift the window in
a vertical direction (up and down) to find its best position with respect to the text trace as in
Figure 3b, which shows how the window is placed to the right of an existing window and needs to
be moved in the vertical direction to find its final position. On the other hand, if the skeleton
exists from the N, then the next window must be placed on top of the current window and moved
horizontally (left or right) so as to be well placed over the text, In some cases where the skeleton
6. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
18
exists from more than one side, then the dividing process will treat each of the branches
separately.
(a) (b)
Figure 3. (a) Initial position of the next window. (b) Window sliding with respect to the
text trace (well placed window).
3.3. Windows Adjustment
Before comparing the similarities between the sub-images (fragments) and saving it on clusters,
the patterns must first be adjusted inside its window in order to prevent the disadvantages of
direct comparison which keep nxn pixel values (for a window size of n) thereby making the
comparisons susceptible to noise and distortion. Thus, an adjustment is done by repositioning the
image trace with respect to its window. We move the shape towards the upper-left corner of the
window as shown in Figure 4, such that only features that are independent of the window
positioning style are computed (in direct comparison). It is important to note that this window
adjustment does not include pattern rotation because the rotated versions are not considered since
they are not produced by the same gesture of the hand and thus should not be used or grouped in
the same class. Also we took into consideration the fact that same scale exists for handwritten
signature images within same sample, since the same writer cannot change the writing scale on
the data set. Thus, two sub-images cannot be compared using this feature because they are not
necessarily scale invariant due to the dataset standardization. We therefore assume that all images
are almost of the same image size and scanned in the same resolution.
Figure 4. Pattern adjustments inside its window
3.4. Features Extraction
Here, we extract the set of features (shape measures) from the patterns and represent the images
in a feature space. Since a typical data analysis problem involves many observations as well as a
good number of respective features, it is important to organize such data in a sensible way before
it can be presented and analysed by humans or machines. The aim of shape characterization is to
obtain shape measures to be used as features for classification in patterns.
For our study, we used “adaptive window positioning” technique for features extraction. This
technique, first proposed by (Siddiqi, Vincent, 2007), is more adapted to the ink trace and has the
flexibility to occupy a line position within a window. Since the images are offline, it is not
possible to follow the stroke trajectory that is followed by the writer. Nevertheless, this method to
some extent seeks to follow the ink trace with the objective of achieving an optimal window
7. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
19
positioning that is based on the analysis of the skeleton of the handwritten Signature image with
respect to the drawing.
3.5 Similarity Measurement
After representing the sub-images from a set of features, then it needed to do a similar measure
among all the windows which enables the comparison between two sub-images (fragments). The
two sub-images are compared with the following correlation similarity measurement:
Where, Nij is the number of pixels of the two sub-images X and Y, which they have the values i
and j respectively, at the corresponding pixel positions. This measure will be close to 1 if the two
compared sub-images are similar and in extreme case it will have a value equal to 1 indicating
that the two shapes are exactly the same.
3.5 Clustering to get the Code book
On this step is the clustering of the adjusted patterns of the sub-images will be done. The
objective is to group similar patterns in the same class, these classes would then correspond to the
frequency patterns occurring in writing. The number of elements per class, however, depends
upon the amount of text in the sample, so the sufficient number cannot be a fixed value. (See
figure 7 for more details).
4. DISCUSSION OF RESULT
In this section, the initial results of the proposed method have been applied and illustrated to
verify the validity of the earlier mentioned procedural methodology in section 3. The work is
implemented using Delphi programming language under Microsoft Windows operating system
environment and a demonstration of the performance is reported at the end of this section
4.1. Pre Processing Information
This is the first step carried out on the scanned signature image. In this step, pre-processing
mechanisms describe converting the image from a grey level image into binary image with
minimal consideration of the noise model [22]. From the image and to make it clearer and more
useful for the signature identification process. Figure 5 shows the before and after pre-processing
for a signature image.
.
(a) (b)
Figure 5. (a) And (b) are before and after the pre-processing respectively
(1)
8. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
20
4.2. Windowing
After identifying the components in an offline signature image, a division (windowing) procedure
was carried out on each component from top-bottom (vertical) and left-right (horizontal) onward
directions of the image trajectory, divided by (13x13) window size (see Figure 6a). Figure 6b
shows a magnified photo of the signature, which gives a clearer view of the windows division all
around the image following the trace trajectory with a well-positioned window indicating that no
overlap exists.
(a) (b)
Figure 6. (a) Offline signatures image division. (b) A closer look at the windows for the
signature part
4.3. Pattern Adjustment
Before moving to the features extraction stage, we adjusted pattern parts inside each window by
moving it to the upper left corner. This makes the calculation of the feature extraction processes
more accurate and easier. Figure 7a shows the patterns extracted from a handwritten signature
image of each window, while Figure 7b illustrates the patterns inside each window after applying
the necessary adjustment on each pattern.
(a) (b)
Figure 7. (a) Shows the extracted patterns. (b) Shows the extracted patterns after making the
adjustment
9. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
21
4.4. Features Extraction
This last three stages are considered the most important phases among all the procedural stages,
due to their impact on the effectiveness of the identification and verification process, the more
related features extraction leads to better categorized codebooks, as a consequence it results in a
better identification process. Figure 8 shows the result of the feature extraction after applying the
techniques mentioned in section 3. For instance, the row zero represents the first window, and
under the HH3 column, is the value 10 which represents the frequency of pattern that accrued in
the signature (please refer to section 3.6). The higher the value, the more it shows a specific
pattern with the original signature in the data set, which implies that this is a high similarity
between the test signature and the data set signature.
Figure 8. Shows the feature extraction
4.5. Similarity Measurement
Here, we classify the many features extracted from the input image into groups in terms of their
similarity attributes. A similarity function mentioned earlier in section 3 was coded in the
software to determine the range of values of the features variety and then classified into groups
according to a specific threshold magnitude (Figure 8).
4.6. Clustering Codebook
Clustering was used to classify the extracted features into classes based on our similarity function.
The number and length of classes varied depending on the authorship of the writer and the
signatures differences. The result of our experiment is illustrated in Figure 9, which shows the
clusters of a given input handwritten signature image, with a total number of 47 classes (c1 to
c47).
10. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
22
Figure 9. Sample Codebook for one Signature using our proposed Adaptive Window Positioning
Technique (A cluster of 47 classes).
4.7. Validation of Result
The validation of our process was tested with a GPDS dataset containing 4870 signature samples
from 90 different writers by comparing the robust features of the test signature with that of the
user’s signature using an appropriate classifier. GPDS is well known and one of the most widely
used database for offline signature identification and verification. In order to evaluate the
performance of the proposed method, we use three standard evaluation criteria: False Acceptance
Rate (FAR), False Rejection Rate (FRR), and Equal Error Rate (ERR).
Table 2. Shows the test result comparison of different methods with our proposed method on
1200 signature of 40 users.
Authors Methods FAR
(%)
FRR
(%)
EER
(%)
Proposed
method
(2014)
Adaptive
Window
Positioning
Techniques
8.68 6.12 7.40
Vargas et. al.,
2011
High Pressure
Polar
Distribution
14.66 10.01 12.33
Larkins et. al.
2009
Adaptive
Feature
Thresholding
10.96 8.16 9.66
Nguyen et.
al., 2009
Global Features
for Offline
Systems
17.25 17.26 17.25
Chen et. al.,
2006
Graph Matching 16.30 16.60 16.40
We used the FAR to account for all the skilled forgeries, FRR for only genuine signatures, and
ERR for verification. The ERR is computed from the average of the values derived from both
FAR and FRR and is a very good criterion for evaluating the accuracy of a method. The method
11. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
23
with the lowest ERR can be considered as the most accurate technique. Hence, results of our
experiment (Table II) reveal that adaptive window positioning technique proved to be the
efficient and most reliable method for accurate signature feature extraction for the identification
of offline handwritten signatures.
4. CONCLUSION
This paper proposed the use of the adaptive window positioning technique for offline handwritten
signature identification. It employed the division of signature images into 13x13 windows and
created some new cluster patterns for each window when classified into groups of similar
attributes. The results of our study show that the adaptive window positioning technique is a more
efficient and reliable method for accurate offline handwritten signature feature extraction. The
major contribution of this paper is that this technique can be employed by signature identification
and verification systems for the detection of offline handwritten signatures signed under duress or
emotional stress.
ACKNOWLEDGMENT
We wish to acknowledge the Faculty of Computing, Universiti Tecknologi Malaysia (UTM) for
their support to this research.
REFERENCES
[1] B. Miroslav, K. Petra, F. Tomislav, (2011) “Basic on-line handwritten signature features for personal
biometric authentication”, MIPRO, Proceedings of the 34th International Convention ,Opatija, May
2011, pp. 1458-1463.
[2] D. R. Shashikumar, K. B. Raja, R. K. Chhotaray, S. Pattanaik, (2010) “Biometric security system
based on signature verification using neural networks”, Computational Intelligence and Computing
Research (ICCIC), (Bangalore), pp 1-6.
[3] G. A. Khuwaja and M. S. Laghari, (2011)“Offline handwritten signature recognition”, World
Academy of Science, Engineering and Technology, vol. 59, pp. 1300-1303.
[4] H. B. Kekre, V. A. Bharadi, (2010) “Gabor filter based feature vector for dynamic signature
recognition”, International Journal of Computer Application, vol. 2 (3), May, pp 74-80.
[5] Y. M. Al-Omari, S. H. S. Abdullah, and K. Omar, (2011) “State-of-the-art in offline signature
verification system”, International Conference on Pattern Analysis and Intelligent Robotics, June 2011,
Putrajaya, (Malaysia), pp. 59-64.
[6] S. Arora, D. Bhattacharjee, M. Nasipuri , L. Malik , M. Kundu and D. K. Basu, (2010) “Performance
comparison of SVM and ANN for handwritten Devnagari character recognition”, International Journal
of Computer Science Issues, vol. 7 (3), May, pp. 1-10.
[7] E. Alattas, and S. Meshoul, (2011)“An effective feature selection method for on-line signature based
authentication”, Eighth International Conference on Fuzzy Systems and Knowledge Discovery
(FSKD), (Shanghai), vol. 3, July, pp.1431-1436.
[8] S. A. Daramola, T. S. Ibiyemi , (2010)“Offline signature recognition using Hidden Markov Model
(HMM)”, International Journal of Computer Applications, vol. 10 (2), November, pp. 17-22.
[9] S. K. Shrivastava, S. Gharde, (2010) “Support vector machine for handwritten Devanagari numeral
recognition” International Journal of Computer Applications (0975 – 8887), vol. 7 (11), October.
[10] D. Samuel, and I.Samuel , (2010) “Novel feature extraction technique for off-line signature
verification system”, International Journal of Engineering Science and Technology ,vol. 2 (7), pp.
3137-3143.
[11] S. K. Shrivastava, and S. S. God, (2010) “Support vector machine for handwritten Devanagari numeral
recognition” International Journal of Computer Applications (0975 – 8887), vol. 7 (11), October.
[12] B. Singh, A. Mittal, and D. Ghosh, (2011)“An evaluation of different feature extractors and classifiers
for offline handwritten Devnagari character recognition”, Journal of Pattern Recognition Research, pp.
269-277.
12. Signal & Image Processing : An International Journal (SIPIJ) Vol.5, No.3, June 2014
24
[13] D. R. Kisku, P. Gupta, and J. K. Sing, (2010)“Offline signature identification by fusion of multiple
classifiers using statistical learning theory”, International Journal of Security and its Applications, vol.
4 (3), July, pp. 35-45.
[14] Siddiqi and Vincent, (2010)"Text independent writer recognition using redundant writing patterns with
contour-based orientation and curvature features", Pattern Recognition, vol. 43, pp. 3853–3865.
[15] Vu Nguyen, M. Blumenstein, V. Muthukkumarasamy, and G. Leedham, (2007)“Off line signature
verification using enhanced modified direction features in conjunction with neural classifiers and
support vector machine”, Ninth International Conference on Document Analysis and Recognition , Vol
2, pp. 734-738.
[16] O. Mirzaei, H. Irani , H. R. Pourreza , (2011)“Offline signature recognition using modular neural
networks with fuzzy response integration”, International Conference on Network and Electronics
Engineering IPCSIT, Vol. 11, (Singapore), pp. 53-59.
[17] M. K. Kalera, S. Sriharly, A. Xu, (2004) "Offline signature verification and identification using
distance statistics", International Journal of Pattern Recognition and Artificial Intelligence, vol. 18 (7),
pp. 1339-1360.
[18] S. M. Odeh and M. Khalil, (2011) “Off-line signature verification and recognition: Neural Network
Approach”, International Conference On Innovations In Intelligent Systems And Applications
(INISTA), pp. 34-38.
[19] M. H. Sigari, M. R. Pourshahabi, and H. R. Prize, (2011)“Off-line handwritten signature identification
and verification using multi-resolution Gabor wavelet”, IJBB, vol. 5, pp.1-15.
[20] M.S. Shirdhonkar and M. Corker, (2011)“Off-line handwritten signature identification using rotated
complex wavelet filters”, International Journal of Computer Science Issues, Vol. 8 (1), January , pp.
478-482.
[21] M. R. Pourshahabi, M. H. Sigari, and H. R. Prize, (2009)"Offline handwritten signature identification
and verification using contourlet transform", International Conference on Soft Computing and Pattern
Recognition, Malacca,(Malaysia), December, pp. 670-673.
[22] M. Rama Bai, (2013)”Composite Texture Shape Classification Based on Morphological Skeleton and
Regional Moments “Signal & Image Processing: An International Journal (SIPIJ), India, Vol.4, No.3,
June, pp. 4313.
AUTHORS
Ghazali Sulong received his BSc degree in statistic from National University of
Malaysia, In 1979, and MSc and PhD in computing from University of Wales ,
Cardiff , United Kingdom , in 1982 and 1989, respectively. He is currently a
professor at the Faculty of Computing , Universiti Teknologi Malaysia . His research
interest includes Biometric – Fingerprint Identification , face recognition , iris
verification, ear recognition, handwriting Recognition, and writer identification ; object
recognition ; medical image segmentation,Enhancement and restoration; human activities recognition; data
hiding - digital watermarking And Steganography ; image encryption; image compression ; image fusion ;
image mining ; Digital image forensics; object detection, segmentation and tracking.
Anwar Yaya Ebrahim received her B.Sc. degree from Babylon University, Iraq in
2000. And her M.Sc. degree from MGM College Dr. Babasaheb Ambedkar
Marathwada University,India in 2009, currently she is PHD.Student in Universiti
Technology Malaysia (UTM). Her Research interests include signatures
identification and verification , features recognition, Image analysis and classification.
Muhammad Jehanzeb received his B.Sc. degree from Arid Agriculture University,
Pakistan in 2005, his M.S.degree from Iqra University, Pakistan, in 2007. He earned his
Ph.D. at Universiti Teknologi Malaysia (UTM) in 2013. Presently, he is working as
Post-Doctoral Fellow at Universiti Teknologi Malaysia (UTM). His research interests
include document analysis and recognition, pattern recognition, image analysis and
classification.