SlideShare a Scribd company logo
Image Processing and Pattern Recognition
3
Contents
• Introduction to Image Processing
• Introduction to Pattern Recognition
4
Introduction to Image Processing
• Image processing is the field that deals with the type of
signal for which the input is an image and output is also
an image.
• As it’s name suggest, it deals with the processing on
image.
5
Introduction to Image processing
Image Processing
Analog Image Processing Digital Image Processing
• 2D Analog signals
• Television image
• Develops a digital system
that performs operation on
an digital image
6
Introduction to Image Processing
Applications:
• Image sharpening and restoration
• Medical field
• Remote sensing
• Transmission and encoding
• Machine/robot vision
• Color processing
• Pattern recognition
• Video processing
• Microscopic imaging
• Others
7
Introduction to Pattern Recognition
• Pattern recognition is the scientific discipline whose goal
is “The classification of objects into a number of
categories or classes”.
• It is an integral part of most machine intelligence
system, build for decision making.
8
Introduction to Pattern Recognition
Application:
• Character (number/letter) recognition
• Computer aided diagnosis
• Speech recognition
• Data mining and knowledge discovery
9
Paper1 (Elsevier Journal)
Title :
A ranking-based feature selection approach for handwritten
character recognition
Year : 2018
Authors:
Nicole Dalia Ciliaa, Claudio De Stefanoa,**, Francesco
Fontanellaa, Alessandra Scotto di Frecaa
(Dipartimento di Ingegneria Elettrica e dell’Informazione, University of Cassino and
Southern Lazio, Via Di Biasio 43, 03043 Cassino (FR), ITALY)
10
• The aim of feature selection is that of reducing the
computational cost of the classification task, in an
attempt to increase, or not to reduce, the classification
performance.
• In the framework of handwriting recognition, the large
variability of the handwriting of different writers makes
the selection of appropriate feature sets even more
complex and have been widely investigated.
11
• To overcome some of the drawbacks by adopting a feature-
ranking-based technique: we considered different univariate
measures to produce a feature ranking and we proposed a
greedy search approach for choosing the feature subset able
to maximize the classification results.
• In the experiments, we considered one of the most effective
and widely used set of features in handwriting recognition to
verify whether our approach allows us to obtain good
classification results by selecting a reduced set of features.
12
• Related work:
The feature selection step consists of three basic steps:
A search procedure for searching candidate feature
subset.
A feature subset evaluation strategy
A stopping criterion
13
• The feature set considered:
The feature of SET1 measures three properties of a
segmented image representing an input sample related to
the concavity, to the contour and to the character surface.
Total 132 features.
The feature set SET2 is used for describing the MFEAT
(multiple feature) dataset, publicly available from the UCI
machine learning repository. Total 649 features divided into
6 groups.
14
FOU:76 Fourier coefficients of the character shapes
ZER:47 Zernike moments
MOR:6 morphological features
KAR:64 karhunen-love coefficients
PIX: 240 pixel averages in 2X3 window
FAC: 216 profile correlation
15
• Feature evaluation:
 Univariate measure
-Chi-square(CS)
-Relief(RF)
-Information gain(IG)
-Gain ratio(GR)
-Symmetrical uncertainty(SU)
 Subset measures
-Consistency criterion(CC)
-Correlation based feature selection criterion(CFS)
16
• Experimental Results:
Three sets of experiments are performed:
 First, we use SET1 for representing the sample of three real word
database, namely NIST, Rimes database, and a db of characters
segmented from postal address(PD)
 Second, we perform a similar analysis but using the SET2.
 Third, we characterized the group features exhibiting higher
discriminant power for both the SET1 and SET2.
 K-NN, Bagging and Random forest are used for evaluation of
selected feature subset.
17
fig: Experimental results on NIST database using K-NN (a), Bagging (b)
and Random Forest (c) classifiers 18
• Conclusion:
The result of experiments suggests that the idea of using
a reduced feature set, namely that obtained by
discarding the features in lower position of the ranking,
can provide very interesting result.
Reducing the computational complexity of the whole
recognition system with very limited effect on the
classification performance.
19
• Future work:
To use other more complex and computationally
expensive feature selection technique on reduced feature
subset, obtained by selecting the features in highest
position on the ranking.
20
Paper 2(IEEE journal)
Title:
Multilingual Character Segmentation and Recognition
Schemes for Indian Document Images
Year : 2018
Author:
Parul Sahare and Sanjay B. Dhok
(Department of Electronics & Communication, Centre of VLSI & Nanotechnology,
Visvesvaraya National Institute of Technology, Nagpur)
21
• robust algorithms for character segmentation and recognition are
presented.
• These documents generally suffer from their layout organizations,
local skews and low print quality and contain intermixed texts
(machineprinted and handwritten).
• In proposed character segmentation algorithm, primary
segmentation paths are obtained using structural property of
characters, whereas overlapped and joined characters are
separated using graph distance theory.
• Finally, segmentation results are validated using highly accurate
Support Vector Machine (SVM) classifier.
22
• For proposed character recognition algorithm, three new
geometrical shape based features are computed. First and
second features are formed with respect to the center pixel
of character, whereas neighborhood information of text
pixels is used for the calculation of third feature.
• For recognizing the input character, k-Nearest Neighbor (k-
NN) classifier is used, as it has intrinsically zero training time.
• Comprehensive experiments are carried out on different
databases containing printed as well as handwritten texts.
23
Fig: structure of proposed work for character segmentation and recognition
24
25
26
• Conclusion:
 In this paper, two new algorithms are proposed for character
segmentation and recognition(FCDF & FCCF) for multilingual Indic
documents consisting of printed and handwritten texts.
 Highest SR of 98.86% is obtained on proprietary database of Latin script.
 Proposed recognition algorithm shows highest accuracy of 99.84% on
Chars74k numerals database.
 Comparatively 0.2-0.5% higher RRs are obtained when k-NN is used with
city block distance relative to other distances. Proposed algorithm is 2.7-
12.4% more efficient on numerals databases as compared to databases
contain alphabets.
27

More Related Content

What's hot

Image Classification using deep learning
Image Classification using deep learning Image Classification using deep learning
Image Classification using deep learning
Asma-AH
 
Action Recognition (Thesis presentation)
Action Recognition (Thesis presentation)Action Recognition (Thesis presentation)
Action Recognition (Thesis presentation)
nikhilus85
 
Digital Image Processing: Image Segmentation
Digital Image Processing: Image SegmentationDigital Image Processing: Image Segmentation
Digital Image Processing: Image Segmentation
Mostafa G. M. Mostafa
 
Image Registration (Digital Image Processing)
Image Registration (Digital Image Processing)Image Registration (Digital Image Processing)
Image Registration (Digital Image Processing)
VARUN KUMAR
 
Human Action Recognition
Human Action RecognitionHuman Action Recognition
Human Action Recognition
NAVER Engineering
 
Sharpening spatial filters
Sharpening spatial filtersSharpening spatial filters
Face recognition ppt
Face recognition pptFace recognition ppt
Face recognition ppt
Santosh Kumar
 
Histogram Specification or Matching Problem
Histogram Specification or Matching ProblemHistogram Specification or Matching Problem
Histogram Specification or Matching Problem
Kalyan Acharjya
 
Computer vision introduction
Computer vision  introduction Computer vision  introduction
Computer vision introduction
Wael Badawy
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
Kuppusamy P
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detection
Brodmann17
 
Hit and-miss transform
Hit and-miss transformHit and-miss transform
Hit and-miss transform
Krish Everglades
 
Pattern Recognition.pptx
Pattern Recognition.pptxPattern Recognition.pptx
Pattern Recognition.pptx
hafeez504942
 
Statistical Pattern recognition(1)
Statistical Pattern recognition(1)Statistical Pattern recognition(1)
Statistical Pattern recognition(1)
Syed Atif Naseem
 
Object recognition
Object recognitionObject recognition
Object recognition
Geraldyne Gengania
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural Network
Richard Kuo
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network Approaches
Fellowship at Vodafone FutureLab
 
PPT on BRAIN TUMOR detection in MRI images based on IMAGE SEGMENTATION
PPT on BRAIN TUMOR detection in MRI images based on  IMAGE SEGMENTATION PPT on BRAIN TUMOR detection in MRI images based on  IMAGE SEGMENTATION
PPT on BRAIN TUMOR detection in MRI images based on IMAGE SEGMENTATION
khanam22
 
Fundamentals of Image Processing & Computer Vision with MATLAB
Fundamentals of Image Processing & Computer Vision with MATLABFundamentals of Image Processing & Computer Vision with MATLAB
Fundamentals of Image Processing & Computer Vision with MATLAB
Ali Ghanbarzadeh
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its Applications
Kasun Chinthaka Piyarathna
 

What's hot (20)

Image Classification using deep learning
Image Classification using deep learning Image Classification using deep learning
Image Classification using deep learning
 
Action Recognition (Thesis presentation)
Action Recognition (Thesis presentation)Action Recognition (Thesis presentation)
Action Recognition (Thesis presentation)
 
Digital Image Processing: Image Segmentation
Digital Image Processing: Image SegmentationDigital Image Processing: Image Segmentation
Digital Image Processing: Image Segmentation
 
Image Registration (Digital Image Processing)
Image Registration (Digital Image Processing)Image Registration (Digital Image Processing)
Image Registration (Digital Image Processing)
 
Human Action Recognition
Human Action RecognitionHuman Action Recognition
Human Action Recognition
 
Sharpening spatial filters
Sharpening spatial filtersSharpening spatial filters
Sharpening spatial filters
 
Face recognition ppt
Face recognition pptFace recognition ppt
Face recognition ppt
 
Histogram Specification or Matching Problem
Histogram Specification or Matching ProblemHistogram Specification or Matching Problem
Histogram Specification or Matching Problem
 
Computer vision introduction
Computer vision  introduction Computer vision  introduction
Computer vision introduction
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
 
Introduction to object detection
Introduction to object detectionIntroduction to object detection
Introduction to object detection
 
Hit and-miss transform
Hit and-miss transformHit and-miss transform
Hit and-miss transform
 
Pattern Recognition.pptx
Pattern Recognition.pptxPattern Recognition.pptx
Pattern Recognition.pptx
 
Statistical Pattern recognition(1)
Statistical Pattern recognition(1)Statistical Pattern recognition(1)
Statistical Pattern recognition(1)
 
Object recognition
Object recognitionObject recognition
Object recognition
 
Machine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural NetworkMachine Learning - Convolutional Neural Network
Machine Learning - Convolutional Neural Network
 
Semantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network ApproachesSemantic segmentation with Convolutional Neural Network Approaches
Semantic segmentation with Convolutional Neural Network Approaches
 
PPT on BRAIN TUMOR detection in MRI images based on IMAGE SEGMENTATION
PPT on BRAIN TUMOR detection in MRI images based on  IMAGE SEGMENTATION PPT on BRAIN TUMOR detection in MRI images based on  IMAGE SEGMENTATION
PPT on BRAIN TUMOR detection in MRI images based on IMAGE SEGMENTATION
 
Fundamentals of Image Processing & Computer Vision with MATLAB
Fundamentals of Image Processing & Computer Vision with MATLABFundamentals of Image Processing & Computer Vision with MATLAB
Fundamentals of Image Processing & Computer Vision with MATLAB
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its Applications
 

Similar to Introduction to image processing and pattern recognition

A Novel Framework For Numerical Character Recognition With Zoning Distance Fe...
A Novel Framework For Numerical Character Recognition With Zoning Distance Fe...A Novel Framework For Numerical Character Recognition With Zoning Distance Fe...
A Novel Framework For Numerical Character Recognition With Zoning Distance Fe...
IJERD Editor
 
AN INTEGRATED APPROACH TO CONTENT BASED IMAGE RETRIEVAL by Madhu
AN INTEGRATED APPROACH TO CONTENT BASED IMAGERETRIEVAL by MadhuAN INTEGRATED APPROACH TO CONTENT BASED IMAGERETRIEVAL by Madhu
AN INTEGRATED APPROACH TO CONTENT BASED IMAGE RETRIEVAL by Madhu
Madhu Rock
 
Assignment-1-NF.docx
Assignment-1-NF.docxAssignment-1-NF.docx
Assignment-1-NF.docx
KhondokerAbuNaim
 
Review of ocr techniques used in automatic mail sorting of postal envelopes
Review of ocr techniques used in automatic mail sorting of postal envelopesReview of ocr techniques used in automatic mail sorting of postal envelopes
Review of ocr techniques used in automatic mail sorting of postal envelopes
sipij
 
Document clustering for forensic analysis an approach for improving compute...
Document clustering for forensic   analysis an approach for improving compute...Document clustering for forensic   analysis an approach for improving compute...
Document clustering for forensic analysis an approach for improving compute...
Madan Golla
 
IRJET - Object Detection using Hausdorff Distance
IRJET -  	  Object Detection using Hausdorff DistanceIRJET -  	  Object Detection using Hausdorff Distance
IRJET - Object Detection using Hausdorff Distance
IRJET Journal
 
IRJET- Object Detection using Hausdorff Distance
IRJET-  	  Object Detection using Hausdorff DistanceIRJET-  	  Object Detection using Hausdorff Distance
IRJET- Object Detection using Hausdorff Distance
IRJET Journal
 
Handwriting_Recognition_using_KNN_classificatiob_algorithm_ijariie6729 (1).pdf
Handwriting_Recognition_using_KNN_classificatiob_algorithm_ijariie6729 (1).pdfHandwriting_Recognition_using_KNN_classificatiob_algorithm_ijariie6729 (1).pdf
Handwriting_Recognition_using_KNN_classificatiob_algorithm_ijariie6729 (1).pdf
Sachin414679
 
Self-Directing Text Detection and Removal from Images with Smoothing
Self-Directing Text Detection and Removal from Images with SmoothingSelf-Directing Text Detection and Removal from Images with Smoothing
Self-Directing Text Detection and Removal from Images with Smoothing
Priyanka Wagh
 
Feature integration for image information retrieval using image mining techni...
Feature integration for image information retrieval using image mining techni...Feature integration for image information retrieval using image mining techni...
Feature integration for image information retrieval using image mining techni...
iaemedu
 
A Review of Feature Extraction Techniques for CBIR based on SVM
A Review of Feature Extraction Techniques for CBIR based on SVMA Review of Feature Extraction Techniques for CBIR based on SVM
A Review of Feature Extraction Techniques for CBIR based on SVM
IJEEE
 
SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.
bhavinecindus
 
C04741319
C04741319C04741319
C04741319
IOSR-JEN
 
Segmentation and recognition of handwritten digit numeral string using a mult...
Segmentation and recognition of handwritten digit numeral string using a mult...Segmentation and recognition of handwritten digit numeral string using a mult...
Segmentation and recognition of handwritten digit numeral string using a mult...
ijfcstjournal
 
Feature Extraction and Feature Selection using Textual Analysis
Feature Extraction and Feature Selection using Textual AnalysisFeature Extraction and Feature Selection using Textual Analysis
Feature Extraction and Feature Selection using Textual Analysis
vivatechijri
 
Comparative study of two methods for Handwritten Devanagari Numeral Recognition
Comparative study of two methods for Handwritten Devanagari Numeral RecognitionComparative study of two methods for Handwritten Devanagari Numeral Recognition
Comparative study of two methods for Handwritten Devanagari Numeral Recognition
IOSR Journals
 
ExplainableAI.pptx
ExplainableAI.pptxExplainableAI.pptx
ExplainableAI.pptx
Andrea Morichetta
 
Image Features Matching and Classification Using Machine Learning
Image Features Matching and Classification Using Machine LearningImage Features Matching and Classification Using Machine Learning
Image Features Matching and Classification Using Machine Learning
IRJET Journal
 
An fpga based efficient fruit recognition system using minimum
An fpga based efficient fruit recognition system using minimumAn fpga based efficient fruit recognition system using minimum
An fpga based efficient fruit recognition system using minimum
Alexander Decker
 
Performance Evaluation Of Ontology And Fuzzybase Cbir
Performance Evaluation Of Ontology And Fuzzybase CbirPerformance Evaluation Of Ontology And Fuzzybase Cbir
Performance Evaluation Of Ontology And Fuzzybase Cbir
acijjournal
 

Similar to Introduction to image processing and pattern recognition (20)

A Novel Framework For Numerical Character Recognition With Zoning Distance Fe...
A Novel Framework For Numerical Character Recognition With Zoning Distance Fe...A Novel Framework For Numerical Character Recognition With Zoning Distance Fe...
A Novel Framework For Numerical Character Recognition With Zoning Distance Fe...
 
AN INTEGRATED APPROACH TO CONTENT BASED IMAGE RETRIEVAL by Madhu
AN INTEGRATED APPROACH TO CONTENT BASED IMAGERETRIEVAL by MadhuAN INTEGRATED APPROACH TO CONTENT BASED IMAGERETRIEVAL by Madhu
AN INTEGRATED APPROACH TO CONTENT BASED IMAGE RETRIEVAL by Madhu
 
Assignment-1-NF.docx
Assignment-1-NF.docxAssignment-1-NF.docx
Assignment-1-NF.docx
 
Review of ocr techniques used in automatic mail sorting of postal envelopes
Review of ocr techniques used in automatic mail sorting of postal envelopesReview of ocr techniques used in automatic mail sorting of postal envelopes
Review of ocr techniques used in automatic mail sorting of postal envelopes
 
Document clustering for forensic analysis an approach for improving compute...
Document clustering for forensic   analysis an approach for improving compute...Document clustering for forensic   analysis an approach for improving compute...
Document clustering for forensic analysis an approach for improving compute...
 
IRJET - Object Detection using Hausdorff Distance
IRJET -  	  Object Detection using Hausdorff DistanceIRJET -  	  Object Detection using Hausdorff Distance
IRJET - Object Detection using Hausdorff Distance
 
IRJET- Object Detection using Hausdorff Distance
IRJET-  	  Object Detection using Hausdorff DistanceIRJET-  	  Object Detection using Hausdorff Distance
IRJET- Object Detection using Hausdorff Distance
 
Handwriting_Recognition_using_KNN_classificatiob_algorithm_ijariie6729 (1).pdf
Handwriting_Recognition_using_KNN_classificatiob_algorithm_ijariie6729 (1).pdfHandwriting_Recognition_using_KNN_classificatiob_algorithm_ijariie6729 (1).pdf
Handwriting_Recognition_using_KNN_classificatiob_algorithm_ijariie6729 (1).pdf
 
Self-Directing Text Detection and Removal from Images with Smoothing
Self-Directing Text Detection and Removal from Images with SmoothingSelf-Directing Text Detection and Removal from Images with Smoothing
Self-Directing Text Detection and Removal from Images with Smoothing
 
Feature integration for image information retrieval using image mining techni...
Feature integration for image information retrieval using image mining techni...Feature integration for image information retrieval using image mining techni...
Feature integration for image information retrieval using image mining techni...
 
A Review of Feature Extraction Techniques for CBIR based on SVM
A Review of Feature Extraction Techniques for CBIR based on SVMA Review of Feature Extraction Techniques for CBIR based on SVM
A Review of Feature Extraction Techniques for CBIR based on SVM
 
SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.
 
C04741319
C04741319C04741319
C04741319
 
Segmentation and recognition of handwritten digit numeral string using a mult...
Segmentation and recognition of handwritten digit numeral string using a mult...Segmentation and recognition of handwritten digit numeral string using a mult...
Segmentation and recognition of handwritten digit numeral string using a mult...
 
Feature Extraction and Feature Selection using Textual Analysis
Feature Extraction and Feature Selection using Textual AnalysisFeature Extraction and Feature Selection using Textual Analysis
Feature Extraction and Feature Selection using Textual Analysis
 
Comparative study of two methods for Handwritten Devanagari Numeral Recognition
Comparative study of two methods for Handwritten Devanagari Numeral RecognitionComparative study of two methods for Handwritten Devanagari Numeral Recognition
Comparative study of two methods for Handwritten Devanagari Numeral Recognition
 
ExplainableAI.pptx
ExplainableAI.pptxExplainableAI.pptx
ExplainableAI.pptx
 
Image Features Matching and Classification Using Machine Learning
Image Features Matching and Classification Using Machine LearningImage Features Matching and Classification Using Machine Learning
Image Features Matching and Classification Using Machine Learning
 
An fpga based efficient fruit recognition system using minimum
An fpga based efficient fruit recognition system using minimumAn fpga based efficient fruit recognition system using minimum
An fpga based efficient fruit recognition system using minimum
 
Performance Evaluation Of Ontology And Fuzzybase Cbir
Performance Evaluation Of Ontology And Fuzzybase CbirPerformance Evaluation Of Ontology And Fuzzybase Cbir
Performance Evaluation Of Ontology And Fuzzybase Cbir
 

Recently uploaded

Manufacturing Process of molasses based distillery ppt.pptx
Manufacturing Process of molasses based distillery ppt.pptxManufacturing Process of molasses based distillery ppt.pptx
Manufacturing Process of molasses based distillery ppt.pptx
Madan Karki
 
Properties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptxProperties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptx
MDSABBIROJJAMANPAYEL
 
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
Mukeshwaran Balu
 
DfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributionsDfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributions
gestioneergodomus
 
Low power architecture of logic gates using adiabatic techniques
Low power architecture of logic gates using adiabatic techniquesLow power architecture of logic gates using adiabatic techniques
Low power architecture of logic gates using adiabatic techniques
nooriasukmaningtyas
 
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
University of Maribor
 
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODELDEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
gerogepatton
 
Understanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine LearningUnderstanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine Learning
SUTEJAS
 
International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...
gerogepatton
 
New techniques for characterising damage in rock slopes.pdf
New techniques for characterising damage in rock slopes.pdfNew techniques for characterising damage in rock slopes.pdf
New techniques for characterising damage in rock slopes.pdf
wisnuprabawa3
 
bank management system in java and mysql report1.pdf
bank management system in java and mysql report1.pdfbank management system in java and mysql report1.pdf
bank management system in java and mysql report1.pdf
Divyam548318
 
ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024
Rahul
 
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesHarnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Christina Lin
 
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
awadeshbabu
 
22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt
KrishnaveniKrishnara1
 
Exception Handling notes in java exception
Exception Handling notes in java exceptionException Handling notes in java exception
Exception Handling notes in java exception
Ratnakar Mikkili
 
Technical Drawings introduction to drawing of prisms
Technical Drawings introduction to drawing of prismsTechnical Drawings introduction to drawing of prisms
Technical Drawings introduction to drawing of prisms
heavyhaig
 
132/33KV substation case study Presentation
132/33KV substation case study Presentation132/33KV substation case study Presentation
132/33KV substation case study Presentation
kandramariana6
 
basic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdfbasic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdf
NidhalKahouli2
 
6th International Conference on Machine Learning & Applications (CMLA 2024)
6th International Conference on Machine Learning & Applications (CMLA 2024)6th International Conference on Machine Learning & Applications (CMLA 2024)
6th International Conference on Machine Learning & Applications (CMLA 2024)
ClaraZara1
 

Recently uploaded (20)

Manufacturing Process of molasses based distillery ppt.pptx
Manufacturing Process of molasses based distillery ppt.pptxManufacturing Process of molasses based distillery ppt.pptx
Manufacturing Process of molasses based distillery ppt.pptx
 
Properties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptxProperties Railway Sleepers and Test.pptx
Properties Railway Sleepers and Test.pptx
 
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
ACRP 4-09 Risk Assessment Method to Support Modification of Airfield Separat...
 
DfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributionsDfMAy 2024 - key insights and contributions
DfMAy 2024 - key insights and contributions
 
Low power architecture of logic gates using adiabatic techniques
Low power architecture of logic gates using adiabatic techniquesLow power architecture of logic gates using adiabatic techniques
Low power architecture of logic gates using adiabatic techniques
 
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...
 
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODELDEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
 
Understanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine LearningUnderstanding Inductive Bias in Machine Learning
Understanding Inductive Bias in Machine Learning
 
International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...International Conference on NLP, Artificial Intelligence, Machine Learning an...
International Conference on NLP, Artificial Intelligence, Machine Learning an...
 
New techniques for characterising damage in rock slopes.pdf
New techniques for characterising damage in rock slopes.pdfNew techniques for characterising damage in rock slopes.pdf
New techniques for characterising damage in rock slopes.pdf
 
bank management system in java and mysql report1.pdf
bank management system in java and mysql report1.pdfbank management system in java and mysql report1.pdf
bank management system in java and mysql report1.pdf
 
ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024ACEP Magazine edition 4th launched on 05.06.2024
ACEP Magazine edition 4th launched on 05.06.2024
 
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming PipelinesHarnessing WebAssembly for Real-time Stateless Streaming Pipelines
Harnessing WebAssembly for Real-time Stateless Streaming Pipelines
 
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
[JPP-1] - (JEE 3.0) - Kinematics 1D - 14th May..pdf
 
22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt
 
Exception Handling notes in java exception
Exception Handling notes in java exceptionException Handling notes in java exception
Exception Handling notes in java exception
 
Technical Drawings introduction to drawing of prisms
Technical Drawings introduction to drawing of prismsTechnical Drawings introduction to drawing of prisms
Technical Drawings introduction to drawing of prisms
 
132/33KV substation case study Presentation
132/33KV substation case study Presentation132/33KV substation case study Presentation
132/33KV substation case study Presentation
 
basic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdfbasic-wireline-operations-course-mahmoud-f-radwan.pdf
basic-wireline-operations-course-mahmoud-f-radwan.pdf
 
6th International Conference on Machine Learning & Applications (CMLA 2024)
6th International Conference on Machine Learning & Applications (CMLA 2024)6th International Conference on Machine Learning & Applications (CMLA 2024)
6th International Conference on Machine Learning & Applications (CMLA 2024)
 

Introduction to image processing and pattern recognition

  • 1. Image Processing and Pattern Recognition 3
  • 2. Contents • Introduction to Image Processing • Introduction to Pattern Recognition 4
  • 3. Introduction to Image Processing • Image processing is the field that deals with the type of signal for which the input is an image and output is also an image. • As it’s name suggest, it deals with the processing on image. 5
  • 4. Introduction to Image processing Image Processing Analog Image Processing Digital Image Processing • 2D Analog signals • Television image • Develops a digital system that performs operation on an digital image 6
  • 5. Introduction to Image Processing Applications: • Image sharpening and restoration • Medical field • Remote sensing • Transmission and encoding • Machine/robot vision • Color processing • Pattern recognition • Video processing • Microscopic imaging • Others 7
  • 6. Introduction to Pattern Recognition • Pattern recognition is the scientific discipline whose goal is “The classification of objects into a number of categories or classes”. • It is an integral part of most machine intelligence system, build for decision making. 8
  • 7. Introduction to Pattern Recognition Application: • Character (number/letter) recognition • Computer aided diagnosis • Speech recognition • Data mining and knowledge discovery 9
  • 8. Paper1 (Elsevier Journal) Title : A ranking-based feature selection approach for handwritten character recognition Year : 2018 Authors: Nicole Dalia Ciliaa, Claudio De Stefanoa,**, Francesco Fontanellaa, Alessandra Scotto di Frecaa (Dipartimento di Ingegneria Elettrica e dell’Informazione, University of Cassino and Southern Lazio, Via Di Biasio 43, 03043 Cassino (FR), ITALY) 10
  • 9. • The aim of feature selection is that of reducing the computational cost of the classification task, in an attempt to increase, or not to reduce, the classification performance. • In the framework of handwriting recognition, the large variability of the handwriting of different writers makes the selection of appropriate feature sets even more complex and have been widely investigated. 11
  • 10. • To overcome some of the drawbacks by adopting a feature- ranking-based technique: we considered different univariate measures to produce a feature ranking and we proposed a greedy search approach for choosing the feature subset able to maximize the classification results. • In the experiments, we considered one of the most effective and widely used set of features in handwriting recognition to verify whether our approach allows us to obtain good classification results by selecting a reduced set of features. 12
  • 11. • Related work: The feature selection step consists of three basic steps: A search procedure for searching candidate feature subset. A feature subset evaluation strategy A stopping criterion 13
  • 12. • The feature set considered: The feature of SET1 measures three properties of a segmented image representing an input sample related to the concavity, to the contour and to the character surface. Total 132 features. The feature set SET2 is used for describing the MFEAT (multiple feature) dataset, publicly available from the UCI machine learning repository. Total 649 features divided into 6 groups. 14
  • 13. FOU:76 Fourier coefficients of the character shapes ZER:47 Zernike moments MOR:6 morphological features KAR:64 karhunen-love coefficients PIX: 240 pixel averages in 2X3 window FAC: 216 profile correlation 15
  • 14. • Feature evaluation:  Univariate measure -Chi-square(CS) -Relief(RF) -Information gain(IG) -Gain ratio(GR) -Symmetrical uncertainty(SU)  Subset measures -Consistency criterion(CC) -Correlation based feature selection criterion(CFS) 16
  • 15. • Experimental Results: Three sets of experiments are performed:  First, we use SET1 for representing the sample of three real word database, namely NIST, Rimes database, and a db of characters segmented from postal address(PD)  Second, we perform a similar analysis but using the SET2.  Third, we characterized the group features exhibiting higher discriminant power for both the SET1 and SET2.  K-NN, Bagging and Random forest are used for evaluation of selected feature subset. 17
  • 16. fig: Experimental results on NIST database using K-NN (a), Bagging (b) and Random Forest (c) classifiers 18
  • 17. • Conclusion: The result of experiments suggests that the idea of using a reduced feature set, namely that obtained by discarding the features in lower position of the ranking, can provide very interesting result. Reducing the computational complexity of the whole recognition system with very limited effect on the classification performance. 19
  • 18. • Future work: To use other more complex and computationally expensive feature selection technique on reduced feature subset, obtained by selecting the features in highest position on the ranking. 20
  • 19. Paper 2(IEEE journal) Title: Multilingual Character Segmentation and Recognition Schemes for Indian Document Images Year : 2018 Author: Parul Sahare and Sanjay B. Dhok (Department of Electronics & Communication, Centre of VLSI & Nanotechnology, Visvesvaraya National Institute of Technology, Nagpur) 21
  • 20. • robust algorithms for character segmentation and recognition are presented. • These documents generally suffer from their layout organizations, local skews and low print quality and contain intermixed texts (machineprinted and handwritten). • In proposed character segmentation algorithm, primary segmentation paths are obtained using structural property of characters, whereas overlapped and joined characters are separated using graph distance theory. • Finally, segmentation results are validated using highly accurate Support Vector Machine (SVM) classifier. 22
  • 21. • For proposed character recognition algorithm, three new geometrical shape based features are computed. First and second features are formed with respect to the center pixel of character, whereas neighborhood information of text pixels is used for the calculation of third feature. • For recognizing the input character, k-Nearest Neighbor (k- NN) classifier is used, as it has intrinsically zero training time. • Comprehensive experiments are carried out on different databases containing printed as well as handwritten texts. 23
  • 22. Fig: structure of proposed work for character segmentation and recognition 24
  • 23. 25
  • 24. 26
  • 25. • Conclusion:  In this paper, two new algorithms are proposed for character segmentation and recognition(FCDF & FCCF) for multilingual Indic documents consisting of printed and handwritten texts.  Highest SR of 98.86% is obtained on proprietary database of Latin script.  Proposed recognition algorithm shows highest accuracy of 99.84% on Chars74k numerals database.  Comparatively 0.2-0.5% higher RRs are obtained when k-NN is used with city block distance relative to other distances. Proposed algorithm is 2.7- 12.4% more efficient on numerals databases as compared to databases contain alphabets. 27