SlideShare a Scribd company logo

A Literature Review on Iris Segmentation Techniques for Iris Recognition Systems

This document reviews various techniques for iris segmentation in iris recognition systems. It discusses 8 techniques: (1) Integrodifferential operator, (2) Hough transform, (3) Masek method, (4) Fuzzy clustering algorithm, (5) Pulling and Pushing method, (6) Eight-neighbor connection based clustering, (7) Segmentation approach based on Fourier spectral density, and (8) Circular Gabor Filter. Each technique achieves some level of segmentation accuracy but also has disadvantages like high computational time, low accuracy, or poor performance on noisy images. The document concludes that a unified framework approach provides the highest overall segmentation accuracy for robustly segmenting iris images.

1 of 5
Download to read offline
IOSR Journal of Computer Engineering (IOSR-JCE)
e-ISSN: 2278-0661, p- ISSN: 2278-8727Volume 11, Issue 1 (May. - Jun. 2013), PP 46-50
www.iosrjournals.org
www.iosrjournals.org 46 | Page
A Literature Review on Iris Segmentation Techniques for Iris
Recognition Systems
Ms. Sruthi.T.K 1,
Ms. Jini.K.M 2
Post Graduate Scholar, Computer Science Department, Nehru college of Engineering, India1
Assistant Professor, Computer Science Department, Nehru College of Engineering, India 2
Abstract—A biometric system offers automatic identification of a human being based on the unique feature or
characteristic which is being possessed by the individual. The iris segmentation has its own major applications
in the field of surveillance as well as in security purposes. The performance of the iris recognition systems
depends heavily on segmentation and normalization techniques. A review of various segmentation approaches
used in iris recognition is done in this paper. The survey is represented in tabular form for quick reference.
Index Terms—iris recognition, biometrics, iris segmentation
I. Introduction
In the recent years, drastic improvements have been accomplished in the areas like iris recognition,
automated iris segmentation, edge detection, boundary detection etc. Iris recognition is a biometric recognition
technology that utilizes the pattern recognition techniques based on the high quality images of iris.. An iris
recognition system mainly uses infrared or else the visible light. The systems which are based on near infrared
light (NIR) are very common because NIR will not generate reflections that makes iris recognition complex.
But, NIR images lacks pigment coloration information, thus recognition algorithms must entirely depend on the
patterns that are unrelated to color. Iris recognition which is based on visible light raise up pigmentation, thus
the recognition systems will be able to exploit the color patterns, which make identification much easier. This is
because, the pigmentation patterns contain a lots of information that can be utilized for recognition. But the
visible light reflections in these types of systems can result in a extensive amount of noise in the gathered
images. A typical iris recognition system consists of mainly three modules. They are image acquisition, pre-
processing stage as well as feature extraction and encoding. Image acquisition is a module which involves the
capturing of iris images with the help of sensors. Pre-processing module provides the determination of the
boundary of iris
within the eye image, and then extracts the iris portion from the image in order to facilitates its
processing. It involves the stages like iris segmentation, iris normalization, image enhancement etc. The
performance of the system has been analyzed in the feature extraction and encoding stage. All these stages
involve their own developments. Major improvements have been made in the field of iris segmentation. In this
paper, some of the methods involving iris segmentation have been analyzed.
Approaches like Integrodifferential operator [1], Hough transform [2] constitute a major part in the iris
recognition techniques. Many other iris recognition as well as the iris segmentation approaches [3,4,5,6,7,8] has
been introduced. Each one has its own advantage as well as the disadvantage. Major drawbacks involved in all
the papers is that, the segmentation accuracy has not been achieved yet. Thus, there is a strong need to develop a
new segmentation approach that is more reliable as well as robust, which can automatically segment non ideal
iris images, which has been acquired using visible illumination in very less constrained imaging environments.
Thus, here a unified framework approach [9] has been introduced, which automatically provide the localized eye
images from face images for iris recognition. And also, an efficient post processing operations has been
introduced in order to mitigate the noisy pixels which have been formed by the misclassification.
II. Approaches Used For Iris Recognition
A. Integrodifferential operator
This approach [1] is regarded as one of the most cited approach in the survey of iris recognition.
Daugman uses an integrodifferential operator for segmenting the iris. It find both inner and the outer boundaries
of the iris region. The outer as well as the inner boundaries are referred to as limbic and pupil boundaries. The
parameters such as the center and radius of the circular boundaries are being searched in the three dimensional
parametric space in order to maximize the evaluation functions involved in the the model. This algorithm
achieves high performance in iris recognition. It is having a drawback that, it suffers from heavy computation.
A Literature review on Iris Segmentation Techniques for Iris Recognition System
www.iosrjournals.org 47 | Page
B. Hough Transform
In this paper, in order to perform personal identification and also the verification, an automated iris
recognition system has been examined as the biometrically based technology. This paper also defines the
technical issues which are being produced while designing an iris recognition system. The technical issues
involve three parts viz. while image acquisition, iris localization and also matching of the extracted iris pattern.
The major challenges involved in the image acquisition are in terms of image resolution and also in the focus
using some standard optics. Here, an extant system has been used in order to provide a remedy to these
challenges. Next issue is the iris localization. That is the image capture during the image acquisition will be a
very larger image which contains iris as a part of it. Thus localization of the part that corresponds to the iris
from acquired image is very much important. The edge detection has been performed through the gradient-based
Canny edge detector, which is followed by the circular Hough transform [2], which is used for iris localization.
The final issue is the pattern matching. After the localization of the region of the acquired image which
corresponds to the iris, the final operation is to decide whether pattern matches with the previously saved iris
pattern. This stage involves alignment, representation, goodness of match and also the decision. All these pattern
matching approaches relies mainly on the method which are closely coupled to the recorded image intensities. If
there occurs a greater variation in any one of the iris, one way to deal with this is the extraction as well as
matching the sets of features that are estimated to be more vigorous to both photometric as well as geometric
distortions in the obtained images. The advantage of this method is that it provides segmentation accuracy up to
an extent. The drawback of this approach is that, it does not provide any attention to eyelid localization (EL),
reflections, eyelashes, and shadows.
C. Masek Method
Masek introduced an open iris recognition system [3] for the verification of human iris uniqueness and
also its performance as the biometrics. The iris recognition system consists of an automated segmentation
system, which localise the iris region from an eye image and also isolate the eyelid, eyelash as well as the
reflection regions. This Automatic segmentation was achieved through the utilization of the circular Hough
transform in order to localise the iris as well as the pupil regions, and the linear Hough transform has been used
for localising the eyelid occlusion. Thresholding has been employed for isolating the eyelashes as well as the
reflections. Now, the segmented iris region has got normalized in order to eliminate the dimensional
inconsistencies between the iris regions. This was achieved by applying a version of Daugman’s rubber sheet
model, in which the iris is modeled as a flexible rubber sheet, which is unpacked into a rectangular block with
constant polar dimensions. Ultimately, the iris features were encoded by convolving the normalized iris region
with the 1D Log-Gabor filters and phase quantizing the output to produce a bit-wise biometric template. For
metric matching, the Hamming distance has been chosen, which provides a measure of number of disagreed bits
between two templates. The drawback of [2] has been recovered in this paper i.e., the localisation of the circular
iris as well as the pupil region, occlusion of eyelids as well as the eyelashes, and also the reflection occurs. The
drawback of this approach is that the iris segmentation is not that much accurate and also the speed of the
system is low.
D. Fuzzy clustering algorithm
A new iris segmentation approach, which has a robust performance in the attendance of heterogeneous
as well as noisy images, has been developed in this. The process starts with the image-feature extraction where
three discrete i.e., (x, y) which corresponds to the pixel position, and z which corresponds to its intensity values
has got extracted for each and every image pixel, which is followed by the application of a clustering algorithm
which is the fuzzy K-means algorithm[4]. This has been used inorder to classify each and every pixel and then
generate the intermediate image. This correspondent image is then used by the edge-detector algorithm. As it
has additional homogeneous characteristics, this eases the tuning of the parameters which were needed by the
edge-detector algorithm. The main advantage of this method is that, it provides a better segmentation for non co-
operative iris recognition. The major drawback in this method is that thorough (extensive) search is needed in
order to recognize the circle parameters of both the pupil as well as the iris boundaries.
E. Pulling and Pushing (PP) Method
A perfect (accurate) as well as a rapid iris segmentation algorithm for iris biometrics has been
developed in this. There are mainly five major contributions in this. Firstly, a novel reflection removal method
has been developed in order to exclude the specularities involved in the input images, also an Adaboost-cascade
iris detector has been used in order to detect the iris in them and also to exclude the non iris image parts before
further processing such that redundant computations can be avoided. In addition to this, a rough iris center has
been extracted in the iris images. Second contribution is that, beginning from the rough iris center, a novel
puling and pushing (PP) [5] procedure has been developed in order to accurately localize the circular iris
A Literature review on Iris Segmentation Techniques for Iris Recognition System
www.iosrjournals.org 48 | Page
boundaries. The PP method directly finds the shortest path to the valid parameters. Third is that, a cubic
smoothing spline has been adopted in order to deal with the noncircular iris boundaries. Fourth contribution is
that, an efficient method for the localization of the eyelids has been developed. The main difficulties of eyelid
localization difficulties such as sharp irregularity of eyelids as well as the noise due to the eyelashes has been
addressed proficiently by a rank filter and also a histogram filter. Finally, the eyelashes as well as the shadows
have been detected with statistically learned prediction model. The advantage of PP method is the accuracy and
speed. The drawback of this method is that the occurrence of the segmentation error.
F. Eight-neighbor connection based clustering
An efficient as well as robust algorithm for noisy iris image segmentation in the background of non
cooperative and less-cooperative iris recognition has been developed in this. The major contributions involved
in this are as follows. Firstly, a novel region growing scheme known as the eight-neighbor connection based
clustering [6] has been proposed in order to cluster the whole iris image into different parts. Then, genuine iris
region has been extracted with the aid of several semantic priors, and also the non-iris regions such as eyelashes,
eyebrow, glass frame, hair, etc are identified and also excluded as well, which intensely reduces the possibility
of mis localizations occurring on the non-iris regions. Secondly, an integrodifferential constellation has been
introduced inorder to accelerate the traditional integrodifferential operator, and then, enhance its global
convergence ability for pupillary as well as the limbic boundary localization. Thirdly, a 1-D horizontal rank
filter as well as an eyelid curvature model has been adopted in order to tackle the eyelashes as well as the shape
irregularity, during eyelid localization. Finally, the eyelash as well as the shadow occlusions has been detected
with the aid of learned prediction model which is based on the intensity statistics between different iris regions.
The advantage of this method is that the iris segmentation accuracy has been attained. The drawback is
segmentation of noisy iris images should be improved.
G. Segmentation approach based on Fourier spectral density
A new segmentation method for noisy frontal view iris images which is captured with minimum cooperation
based on the Fourier spectral density [7] has been proposed in this paper. This approach computes the Fourier
spectral density for each pixel with the aid of its neighborhood and then executes row-wise adaptive
thresholding, and thus results in a binary image which gives the iris region in a fairly accurate manner. This
segmentation method can also be used in order to calculate limbic as well as the pupil boundaries. This is having
the advantage that, this has lower computations as compared to that of [1], [2]. The drawback is that, limbic
boundary detection should be improved.
H. Circular Gabor Filter
Segmentation of iris is one of the most vital as well as difficult task in iris recognition. [1] and [2] are
widely used for iris texture segmentation. But their computational time consumption is high. Time consumption
is mainly required in order to recognize the initial centers of both iris as well as pupil circular boundaries. A
simple solution for this problem has been given in this paper. The circular Gabor filter (CGF) [8] has been
utilized in order to localize the initial pupil center. The main advantage of this approach is that the segmentation
accuracy for both the pupil as well as the iris boundaries has been achieved. The drawback is that, the overall
segmentation accuracy is less than that of [9].
All these techniques have improved the performance of the iris recognition system. All these
techniques acquire segmentation accuracy in many areas such as boundary detection, iris detection, pupil and
limbic boundary detection etc. But none of these papers provide a solution for attaining overall segmentation
accuracy. Thus there is a an extreme need for developing a new segmentation method, which are more reliable
as well as robust for automatically segmenting the non ideal iris images.
This paper introduces a unified solution for iris segmentation [9]. Here, a new iris segmentation
framework has been developed, which can robustly segment the iris images attained using NIR or else the
visible illumination. This approach exploits multiple higher order local pixel dependencies using Zernike
moments (ZM), in order to strongly (robustly) classify the eye region pixels into iris or else the non iris regions
using trained neural network/ support vector machine (NN/SVM) classifiers. Image enhancement using single
scale retinex (SSR) algorithm has been employed for illumination variation problem. Face as well as the eye
detection modules has been integrated in the unified framework to automatically provide the localized eye
region from facial image for segmenting the iris. A robust post processing operations algorithm has been
developed inorder to effectively alleviate the noisy pixels which has been caused due to misclassification.
A Literature review on Iris Segmentation Techniques for Iris Recognition System
www.iosrjournals.org 49 | Page
Table1: Comparison table on literature survey
III. Conclusion
This paper presents a literature survey on the various segmentation techniques involved in iris
recognition. There are various techniques that can be used for this purpose. Overall segmentation accuracy of all
these techniques has been analyzed. Higher the segmentation rate, thus higher is its performance The unified
framework has the highest segmentation rate and also has highest performance.
NAME METHOD PERFORMANCE DISADVANTAGES
High confidence
visual recognition of
persons by a test of
statistical
independence
Integrodifferential
operator
High performance in
iris recognition
Computational time is
very high
Iris Recognition: An
emerging biometric
technology
Hough transform Segmentation
accuracy achieved
up to an extent
Does not provide
attention to EL as well
as reflections etc
Recognition of
Human Iris Patterns
for Biometric
Identification
Liber Masek’s
encoding algorithm
Localization of
circular iris region
as well as eyelids,
eyelashes and also
the reflections
occurs
Speed of the system is
low
Iris segmentation
methodology for
non cooperative
recognition
Fuzzy clustering
algorithm
Better segmentation
for non co-operative
iris recognition
Thorough search is
needed to recognize
the circle parameters
of both pupil and iris
boundaries
Toward Accurate
and Fast Iris
Segmentation for
Iris Biometrics
Pushing and pulling
(PP) method
Possess accuracy
and speed
Occurrence of
segmentation error
Efficient and robust
segmentation of
noisy iris images for
non cooperative
iris recognition
Eight-neighbor
connection based
clustering
iris segmentation
accuracy has been
attained to an extent
segmentation of noisy
iris images should be
improved
Efficient
segmentation
technique for noisy
frontal view iris
images using
Fourier spectral
density
Segmentation
approach based on
Fourier spectral
density
Computational
complexity is low
Limbic boundary
detection should be
improved.
Iris Segmentation in
Visible Wavelength
Environment
Circular Gabor
Filter
segmentation
accuracy for both
the pupil as well as
the iris boundaries
has been achieved
Over all segmentation
accuracy is less than
that of the unified
framework approach
A Literature review on Iris Segmentation Techniques for Iris Recognition System
www.iosrjournals.org 50 | Page
References
[1] J.G. Daugman, High confidence visual recognition of persons by a test of statistical independence, IEEE Transactions on Pattern
Analysis and Machine Intelligence, 15, p.1148, Nov 1993
[2] R.P. Wildes, Iris recognition: An emerging biometric technology, Proceedings of the IEEE, 85 p.1348, sep. 1997
[3] L. Masek, ―Recognition of Human Iris Patterns for Biometric Identification‖, M.S. Dissertation, the University of Western
Australia, 2003
[4] H. Proença, L.A. Alexandre, ―Iris segmentation methodology for non-cooperative recognition‖, IEE Proceedings of Vision, Image
and Signal Processing, pp. 199-205, 2006
[5] Z. He, T. Tan, Z. Sun, and X. Qiu, ―Toward accurate and fast iris segmentation for iris biometrics,‖ IEEE Trans. Pattern Anal.
Machine Intelligence, vol. 31, no. 9, pp. 1670–1684, Sep. 2009.
[6] T. Tan, Z. He, and Z. Sun, ―Efficient and robust segmentation of noisy iris images for non-cooperative iris recognition,‖ Image Vis.
Comput., vol. 28, no. 2, pp. 223–230, Feb. 2010.
[7] N.B. Puhan, N. Sudha, A. Sivaraman Kaushalram, Efficient segmentation technique for noisy frontal view iris images using Fourier
spectral density, Signal, Image and Video Processing, 5, p. 105, 2011.
[8] Radman, A., Jumari, K., and Zainal, N, Iris segmentation in visible wavelength environment. Procedia Engineering, 41:743–748,
2012
[9] Tan, C. and Kumar, A., Unified framework for automated iris segmentation using distantly acquired face images. IEEE
Transactions on Image Processing, 21(9):4068–4079, S

Recommended

International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)ijceronline
 
EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...
EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...
EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...IJNSA Journal
 
IRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATOR
IRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATORIRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATOR
IRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATORcscpconf
 
The Biometric Algorithm based on Fusion of DWT Frequency Components of Enhanc...
The Biometric Algorithm based on Fusion of DWT Frequency Components of Enhanc...The Biometric Algorithm based on Fusion of DWT Frequency Components of Enhanc...
The Biometric Algorithm based on Fusion of DWT Frequency Components of Enhanc...CSCJournals
 
Iris recognition for personal identification using lamstar neural network
Iris recognition for personal identification using lamstar neural networkIris recognition for personal identification using lamstar neural network
Iris recognition for personal identification using lamstar neural networkijcsit
 
IRJET- Survey of Iris Recognition Techniques
IRJET- Survey of Iris Recognition TechniquesIRJET- Survey of Iris Recognition Techniques
IRJET- Survey of Iris Recognition TechniquesIRJET Journal
 
International Journal of Computer Science, Engineering and Information Techno...
International Journal of Computer Science, Engineering and Information Techno...International Journal of Computer Science, Engineering and Information Techno...
International Journal of Computer Science, Engineering and Information Techno...ijcseit
 

More Related Content

What's hot

WAVELET PACKET BASED IRIS TEXTURE ANALYSIS FOR PERSON AUTHENTICATION
WAVELET PACKET BASED IRIS TEXTURE ANALYSIS FOR PERSON AUTHENTICATIONWAVELET PACKET BASED IRIS TEXTURE ANALYSIS FOR PERSON AUTHENTICATION
WAVELET PACKET BASED IRIS TEXTURE ANALYSIS FOR PERSON AUTHENTICATIONsipij
 
A robust iris recognition method on adverse conditions
A robust iris recognition method on adverse conditionsA robust iris recognition method on adverse conditions
A robust iris recognition method on adverse conditionsijcseit
 
Implementation of features dynamic tracking filter to tracing pupils
Implementation of features dynamic tracking filter to tracing pupilsImplementation of features dynamic tracking filter to tracing pupils
Implementation of features dynamic tracking filter to tracing pupilssipij
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)IJERD Editor
 
A Survey : Iris Based Recognition Systems
A Survey : Iris Based Recognition SystemsA Survey : Iris Based Recognition Systems
A Survey : Iris Based Recognition SystemsEditor IJMTER
 
Transform Domain Based Iris Recognition using EMD and FFT
Transform Domain Based Iris Recognition using EMD and FFTTransform Domain Based Iris Recognition using EMD and FFT
Transform Domain Based Iris Recognition using EMD and FFTIOSRJVSP
 
Iris Segmentation: a survey
Iris Segmentation: a surveyIris Segmentation: a survey
Iris Segmentation: a surveyIJMER
 
IRDO: Iris Recognition by fusion of DTCWT and OLBP
IRDO: Iris Recognition by fusion of DTCWT and OLBPIRDO: Iris Recognition by fusion of DTCWT and OLBP
IRDO: Iris Recognition by fusion of DTCWT and OLBPIJERA Editor
 
Retinal Macular Edema Detection Using Optical Coherence Tomography Images
Retinal Macular Edema Detection Using Optical Coherence Tomography ImagesRetinal Macular Edema Detection Using Optical Coherence Tomography Images
Retinal Macular Edema Detection Using Optical Coherence Tomography ImagesIOSRJVSP
 
Ieeepro techno solutions ieee embedded project secure and robust iris recog...
Ieeepro techno solutions   ieee embedded project secure and robust iris recog...Ieeepro techno solutions   ieee embedded project secure and robust iris recog...
Ieeepro techno solutions ieee embedded project secure and robust iris recog...srinivasanece7
 
A03640106
A03640106A03640106
A03640106theijes
 
MULTI SCALE ICA BASED IRIS RECOGNITION USING BSIF AND HOG
MULTI SCALE ICA BASED IRIS RECOGNITION USING BSIF AND HOG MULTI SCALE ICA BASED IRIS RECOGNITION USING BSIF AND HOG
MULTI SCALE ICA BASED IRIS RECOGNITION USING BSIF AND HOG sipij
 
A Survey on Retinal Area Detector From Scanning Laser Ophthalmoscope (SLO) Im...
A Survey on Retinal Area Detector From Scanning Laser Ophthalmoscope (SLO) Im...A Survey on Retinal Area Detector From Scanning Laser Ophthalmoscope (SLO) Im...
A Survey on Retinal Area Detector From Scanning Laser Ophthalmoscope (SLO) Im...IRJET Journal
 
Detection of exudates draft
Detection of exudates draftDetection of exudates draft
Detection of exudates draftnitheshksuvarna
 
Detection of exudates draft
Detection of exudates draftDetection of exudates draft
Detection of exudates draftnitheshksuvarna
 

What's hot (19)

WAVELET PACKET BASED IRIS TEXTURE ANALYSIS FOR PERSON AUTHENTICATION
WAVELET PACKET BASED IRIS TEXTURE ANALYSIS FOR PERSON AUTHENTICATIONWAVELET PACKET BASED IRIS TEXTURE ANALYSIS FOR PERSON AUTHENTICATION
WAVELET PACKET BASED IRIS TEXTURE ANALYSIS FOR PERSON AUTHENTICATION
 
E010222124
E010222124E010222124
E010222124
 
A robust iris recognition method on adverse conditions
A robust iris recognition method on adverse conditionsA robust iris recognition method on adverse conditions
A robust iris recognition method on adverse conditions
 
K0966468
K0966468K0966468
K0966468
 
Implementation of features dynamic tracking filter to tracing pupils
Implementation of features dynamic tracking filter to tracing pupilsImplementation of features dynamic tracking filter to tracing pupils
Implementation of features dynamic tracking filter to tracing pupils
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
 
A Survey : Iris Based Recognition Systems
A Survey : Iris Based Recognition SystemsA Survey : Iris Based Recognition Systems
A Survey : Iris Based Recognition Systems
 
Transform Domain Based Iris Recognition using EMD and FFT
Transform Domain Based Iris Recognition using EMD and FFTTransform Domain Based Iris Recognition using EMD and FFT
Transform Domain Based Iris Recognition using EMD and FFT
 
23-02-03[1]
23-02-03[1]23-02-03[1]
23-02-03[1]
 
Iris Segmentation: a survey
Iris Segmentation: a surveyIris Segmentation: a survey
Iris Segmentation: a survey
 
A SURVEY ON IRIS RECOGNITION FOR AUTHENTICATION
A SURVEY ON IRIS RECOGNITION FOR AUTHENTICATIONA SURVEY ON IRIS RECOGNITION FOR AUTHENTICATION
A SURVEY ON IRIS RECOGNITION FOR AUTHENTICATION
 
IRDO: Iris Recognition by fusion of DTCWT and OLBP
IRDO: Iris Recognition by fusion of DTCWT and OLBPIRDO: Iris Recognition by fusion of DTCWT and OLBP
IRDO: Iris Recognition by fusion of DTCWT and OLBP
 
Retinal Macular Edema Detection Using Optical Coherence Tomography Images
Retinal Macular Edema Detection Using Optical Coherence Tomography ImagesRetinal Macular Edema Detection Using Optical Coherence Tomography Images
Retinal Macular Edema Detection Using Optical Coherence Tomography Images
 
Ieeepro techno solutions ieee embedded project secure and robust iris recog...
Ieeepro techno solutions   ieee embedded project secure and robust iris recog...Ieeepro techno solutions   ieee embedded project secure and robust iris recog...
Ieeepro techno solutions ieee embedded project secure and robust iris recog...
 
A03640106
A03640106A03640106
A03640106
 
MULTI SCALE ICA BASED IRIS RECOGNITION USING BSIF AND HOG
MULTI SCALE ICA BASED IRIS RECOGNITION USING BSIF AND HOG MULTI SCALE ICA BASED IRIS RECOGNITION USING BSIF AND HOG
MULTI SCALE ICA BASED IRIS RECOGNITION USING BSIF AND HOG
 
A Survey on Retinal Area Detector From Scanning Laser Ophthalmoscope (SLO) Im...
A Survey on Retinal Area Detector From Scanning Laser Ophthalmoscope (SLO) Im...A Survey on Retinal Area Detector From Scanning Laser Ophthalmoscope (SLO) Im...
A Survey on Retinal Area Detector From Scanning Laser Ophthalmoscope (SLO) Im...
 
Detection of exudates draft
Detection of exudates draftDetection of exudates draft
Detection of exudates draft
 
Detection of exudates draft
Detection of exudates draftDetection of exudates draft
Detection of exudates draft
 

Viewers also liked

Review of Image Segmentation Techniques based on Region Merging Approach
Review of Image Segmentation Techniques based on Region Merging ApproachReview of Image Segmentation Techniques based on Region Merging Approach
Review of Image Segmentation Techniques based on Region Merging ApproachEditor IJMTER
 
DETECTING AND COUNTING THE NO. OF WHITE BLOOD CELLS IN BLOOD SAMPLE IMAGES BY...
DETECTING AND COUNTING THE NO. OF WHITE BLOOD CELLS IN BLOOD SAMPLE IMAGES BY...DETECTING AND COUNTING THE NO. OF WHITE BLOOD CELLS IN BLOOD SAMPLE IMAGES BY...
DETECTING AND COUNTING THE NO. OF WHITE BLOOD CELLS IN BLOOD SAMPLE IMAGES BY...IJEEE
 
IMAGE SEGMENTATION TECHNIQUES
IMAGE SEGMENTATION TECHNIQUESIMAGE SEGMENTATION TECHNIQUES
IMAGE SEGMENTATION TECHNIQUESVicky Kumar
 
Automatic Blood Vessels Segmentation of Retinal Images
Automatic Blood Vessels Segmentation of Retinal ImagesAutomatic Blood Vessels Segmentation of Retinal Images
Automatic Blood Vessels Segmentation of Retinal ImagesHarish Rajula
 
Image segmentation
Image segmentationImage segmentation
Image segmentationRania H
 
Image segmentation
Image segmentationImage segmentation
Image segmentationMukul Jindal
 
Image segmentation
Image segmentationImage segmentation
Image segmentationDeepak Kumar
 
CANCER CELL DETECTION USING DIGITAL IMAGE PROCESSING
CANCER  CELL  DETECTION USING DIGITAL IMAGE PROCESSINGCANCER  CELL  DETECTION USING DIGITAL IMAGE PROCESSING
CANCER CELL DETECTION USING DIGITAL IMAGE PROCESSINGkajikho9
 
Image segmentation ppt
Image segmentation pptImage segmentation ppt
Image segmentation pptGichelle Amon
 
Paper id 212014108
Paper id 212014108Paper id 212014108
Paper id 212014108IJRAT
 

Viewers also liked (14)

Review of Image Segmentation Techniques based on Region Merging Approach
Review of Image Segmentation Techniques based on Region Merging ApproachReview of Image Segmentation Techniques based on Region Merging Approach
Review of Image Segmentation Techniques based on Region Merging Approach
 
DETECTING AND COUNTING THE NO. OF WHITE BLOOD CELLS IN BLOOD SAMPLE IMAGES BY...
DETECTING AND COUNTING THE NO. OF WHITE BLOOD CELLS IN BLOOD SAMPLE IMAGES BY...DETECTING AND COUNTING THE NO. OF WHITE BLOOD CELLS IN BLOOD SAMPLE IMAGES BY...
DETECTING AND COUNTING THE NO. OF WHITE BLOOD CELLS IN BLOOD SAMPLE IMAGES BY...
 
Segmentation Techniques -I
Segmentation Techniques -ISegmentation Techniques -I
Segmentation Techniques -I
 
Segmentation Techniques -II
Segmentation Techniques -IISegmentation Techniques -II
Segmentation Techniques -II
 
IMAGE SEGMENTATION TECHNIQUES
IMAGE SEGMENTATION TECHNIQUESIMAGE SEGMENTATION TECHNIQUES
IMAGE SEGMENTATION TECHNIQUES
 
Automatic Blood Vessels Segmentation of Retinal Images
Automatic Blood Vessels Segmentation of Retinal ImagesAutomatic Blood Vessels Segmentation of Retinal Images
Automatic Blood Vessels Segmentation of Retinal Images
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
 
Segmentation
SegmentationSegmentation
Segmentation
 
CANCER CELL DETECTION USING DIGITAL IMAGE PROCESSING
CANCER  CELL  DETECTION USING DIGITAL IMAGE PROCESSINGCANCER  CELL  DETECTION USING DIGITAL IMAGE PROCESSING
CANCER CELL DETECTION USING DIGITAL IMAGE PROCESSING
 
IMAGE SEGMENTATION.
IMAGE SEGMENTATION.IMAGE SEGMENTATION.
IMAGE SEGMENTATION.
 
Image segmentation ppt
Image segmentation pptImage segmentation ppt
Image segmentation ppt
 
Paper id 212014108
Paper id 212014108Paper id 212014108
Paper id 212014108
 

Similar to A Literature Review on Iris Segmentation Techniques for Iris Recognition Systems

EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...
EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...
EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...IJNSA Journal
 
Iris recognition based on 2D Gabor filter
Iris recognition based on 2D Gabor filterIris recognition based on 2D Gabor filter
Iris recognition based on 2D Gabor filterIJECEIAES
 
IRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATOR
IRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATORIRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATOR
IRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATORcsitconf
 
Ijarcet vol-2-issue-4-1352-1356
Ijarcet vol-2-issue-4-1352-1356Ijarcet vol-2-issue-4-1352-1356
Ijarcet vol-2-issue-4-1352-1356Editor IJARCET
 
International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)inventionjournals
 
Biometric Iris Recognition Based on Hybrid Technique
Biometric Iris Recognition Based on Hybrid TechniqueBiometric Iris Recognition Based on Hybrid Technique
Biometric Iris Recognition Based on Hybrid Techniqueijsc
 
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...Editor IJCATR
 
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...Editor IJCATR
 
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...Editor IJCATR
 
IRJET-Unconstraint Eye Tracking on Mobile Smartphone
IRJET-Unconstraint Eye Tracking on Mobile SmartphoneIRJET-Unconstraint Eye Tracking on Mobile Smartphone
IRJET-Unconstraint Eye Tracking on Mobile SmartphoneIRJET Journal
 
Biometric Iris Recognition Based on Hybrid Technique
Biometric Iris Recognition Based on Hybrid Technique  Biometric Iris Recognition Based on Hybrid Technique
Biometric Iris Recognition Based on Hybrid Technique ijsc
 
A survey paper on various biometric security system methods
A survey paper on various biometric security system methodsA survey paper on various biometric security system methods
A survey paper on various biometric security system methodsIRJET Journal
 

Similar to A Literature Review on Iris Segmentation Techniques for Iris Recognition Systems (15)

EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...
EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...
EFFECTIVENESS OF FEATURE DETECTION OPERATORS ON THE PERFORMANCE OF IRIS BIOME...
 
Iris recognition based on 2D Gabor filter
Iris recognition based on 2D Gabor filterIris recognition based on 2D Gabor filter
Iris recognition based on 2D Gabor filter
 
IRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATOR
IRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATORIRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATOR
IRIS BIOMETRIC RECOGNITION SYSTEM EMPLOYING CANNY OPERATOR
 
Ijarcet vol-2-issue-4-1352-1356
Ijarcet vol-2-issue-4-1352-1356Ijarcet vol-2-issue-4-1352-1356
Ijarcet vol-2-issue-4-1352-1356
 
International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)
 
Biometric Iris Recognition Based on Hybrid Technique
Biometric Iris Recognition Based on Hybrid TechniqueBiometric Iris Recognition Based on Hybrid Technique
Biometric Iris Recognition Based on Hybrid Technique
 
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
 
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
 
D45012128
D45012128D45012128
D45012128
 
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
Evaluation of Iris Recognition System on Multiple Feature Extraction Algorith...
 
IRJET-Unconstraint Eye Tracking on Mobile Smartphone
IRJET-Unconstraint Eye Tracking on Mobile SmartphoneIRJET-Unconstraint Eye Tracking on Mobile Smartphone
IRJET-Unconstraint Eye Tracking on Mobile Smartphone
 
Biometric Iris Recognition Based on Hybrid Technique
Biometric Iris Recognition Based on Hybrid Technique  Biometric Iris Recognition Based on Hybrid Technique
Biometric Iris Recognition Based on Hybrid Technique
 
Multibiometrics ver5
Multibiometrics ver5Multibiometrics ver5
Multibiometrics ver5
 
E017443136
E017443136E017443136
E017443136
 
A survey paper on various biometric security system methods
A survey paper on various biometric security system methodsA survey paper on various biometric security system methods
A survey paper on various biometric security system methods
 

More from IOSR Journals (20)

A011140104
A011140104A011140104
A011140104
 
M0111397100
M0111397100M0111397100
M0111397100
 
L011138596
L011138596L011138596
L011138596
 
K011138084
K011138084K011138084
K011138084
 
J011137479
J011137479J011137479
J011137479
 
I011136673
I011136673I011136673
I011136673
 
G011134454
G011134454G011134454
G011134454
 
H011135565
H011135565H011135565
H011135565
 
F011134043
F011134043F011134043
F011134043
 
E011133639
E011133639E011133639
E011133639
 
D011132635
D011132635D011132635
D011132635
 
C011131925
C011131925C011131925
C011131925
 
B011130918
B011130918B011130918
B011130918
 
A011130108
A011130108A011130108
A011130108
 
I011125160
I011125160I011125160
I011125160
 
H011124050
H011124050H011124050
H011124050
 
G011123539
G011123539G011123539
G011123539
 
F011123134
F011123134F011123134
F011123134
 
E011122530
E011122530E011122530
E011122530
 
D011121524
D011121524D011121524
D011121524
 

Recently uploaded

Application of eddy current in industry and domestic purposes.pptx
Application of eddy current in industry and domestic purposes.pptxApplication of eddy current in industry and domestic purposes.pptx
Application of eddy current in industry and domestic purposes.pptxsukantatechedu
 
MedTech R&D - Tamer Emara - resume @2024
MedTech R&D - Tamer Emara - resume @2024MedTech R&D - Tamer Emara - resume @2024
MedTech R&D - Tamer Emara - resume @2024Tamer Emara
 
ELMAR pressure control presentation.pptx
ELMAR pressure control presentation.pptxELMAR pressure control presentation.pptx
ELMAR pressure control presentation.pptxArman572583
 
CHAPTER 1_ HTML and CSS Introduction Module
CHAPTER 1_ HTML and CSS Introduction ModuleCHAPTER 1_ HTML and CSS Introduction Module
CHAPTER 1_ HTML and CSS Introduction Modulessusera4f8281
 
CCW332-DIGITAL MARKETING QUESTION BANK WITH ANSWERS
CCW332-DIGITAL MARKETING QUESTION BANK WITH ANSWERSCCW332-DIGITAL MARKETING QUESTION BANK WITH ANSWERS
CCW332-DIGITAL MARKETING QUESTION BANK WITH ANSWERSTamil949112
 
Basic Instrumentation Symbols | P&ID | PFD | Gaurav Singh Rajput
Basic Instrumentation Symbols | P&ID | PFD | Gaurav Singh RajputBasic Instrumentation Symbols | P&ID | PFD | Gaurav Singh Rajput
Basic Instrumentation Symbols | P&ID | PFD | Gaurav Singh RajputGaurav Singh Rajput
 
Chapter 1 - Drilling Fluid Functions GR.ppt
Chapter 1 - Drilling Fluid Functions GR.pptChapter 1 - Drilling Fluid Functions GR.ppt
Chapter 1 - Drilling Fluid Functions GR.pptzeidali3
 
HB Self-Body characteristics UHV understanding
HB Self-Body characteristics UHV understandingHB Self-Body characteristics UHV understanding
HB Self-Body characteristics UHV understandingLeoRaju4
 
Microservices: Benefits, drawbacks and are they for me?
Microservices: Benefits, drawbacks and are they for me?Microservices: Benefits, drawbacks and are they for me?
Microservices: Benefits, drawbacks and are they for me?Marian Marinov
 
Chase Commerce Center History Nordberg manufacturing Rexnord Global power com...
Chase Commerce Center History Nordberg manufacturing Rexnord Global power com...Chase Commerce Center History Nordberg manufacturing Rexnord Global power com...
Chase Commerce Center History Nordberg manufacturing Rexnord Global power com...drezdzond
 
Checklist to troubleshoot CD moisture profiles.docx
Checklist to troubleshoot CD moisture profiles.docxChecklist to troubleshoot CD moisture profiles.docx
Checklist to troubleshoot CD moisture profiles.docxNoman khan
 
Model Approved Food/ sanitary Grade Flow Meter
Model Approved Food/ sanitary Grade Flow MeterModel Approved Food/ sanitary Grade Flow Meter
Model Approved Food/ sanitary Grade Flow MeterManasMicrosystems
 
B111_FTS_2011.06.01 Fuel Tank Safety.pdf
B111_FTS_2011.06.01 Fuel Tank Safety.pdfB111_FTS_2011.06.01 Fuel Tank Safety.pdf
B111_FTS_2011.06.01 Fuel Tank Safety.pdfKhoiTruong19
 
【文凭定制】坎特伯雷大学毕业证学历认证
【文凭定制】坎特伯雷大学毕业证学历认证【文凭定制】坎特伯雷大学毕业证学历认证
【文凭定制】坎特伯雷大学毕业证学历认证muvgemo
 
Center Enamel is the leading bolted steel tanks manufacturer in China.docx
Center Enamel is the leading bolted steel tanks manufacturer in China.docxCenter Enamel is the leading bolted steel tanks manufacturer in China.docx
Center Enamel is the leading bolted steel tanks manufacturer in China.docxsjzzztc
 
Basic Concepts of Material Science for Electrical and Electronic Materials ...
Basic Concepts of Material Science for  Electrical and Electronic Materials  ...Basic Concepts of Material Science for  Electrical and Electronic Materials  ...
Basic Concepts of Material Science for Electrical and Electronic Materials ...PeopleFinder
 
ChoiAccess.pptbuhuhujhhuhuhuhuhuhhhhhhhhhhhhh
ChoiAccess.pptbuhuhujhhuhuhuhuhuhhhhhhhhhhhhhChoiAccess.pptbuhuhujhhuhuhuhuhuhhhhhhhhhhhhh
ChoiAccess.pptbuhuhujhhuhuhuhuhuhhhhhhhhhhhhhhazhamina
 
1 Energy Management for Lighting Systems.pptx
1 Energy Management for Lighting Systems.pptx1 Energy Management for Lighting Systems.pptx
1 Energy Management for Lighting Systems.pptxrevathiragavi77
 
21 SCHEME_21EC53_VTU_MODULE-4_COMPUTER COMMUNCATION NETWORK.pdf
21 SCHEME_21EC53_VTU_MODULE-4_COMPUTER COMMUNCATION NETWORK.pdf21 SCHEME_21EC53_VTU_MODULE-4_COMPUTER COMMUNCATION NETWORK.pdf
21 SCHEME_21EC53_VTU_MODULE-4_COMPUTER COMMUNCATION NETWORK.pdfDr. Shivashankar
 

Recently uploaded (20)

Application of eddy current in industry and domestic purposes.pptx
Application of eddy current in industry and domestic purposes.pptxApplication of eddy current in industry and domestic purposes.pptx
Application of eddy current in industry and domestic purposes.pptx
 
MedTech R&D - Tamer Emara - resume @2024
MedTech R&D - Tamer Emara - resume @2024MedTech R&D - Tamer Emara - resume @2024
MedTech R&D - Tamer Emara - resume @2024
 
ELMAR pressure control presentation.pptx
ELMAR pressure control presentation.pptxELMAR pressure control presentation.pptx
ELMAR pressure control presentation.pptx
 
CHAPTER 1_ HTML and CSS Introduction Module
CHAPTER 1_ HTML and CSS Introduction ModuleCHAPTER 1_ HTML and CSS Introduction Module
CHAPTER 1_ HTML and CSS Introduction Module
 
CCW332-DIGITAL MARKETING QUESTION BANK WITH ANSWERS
CCW332-DIGITAL MARKETING QUESTION BANK WITH ANSWERSCCW332-DIGITAL MARKETING QUESTION BANK WITH ANSWERS
CCW332-DIGITAL MARKETING QUESTION BANK WITH ANSWERS
 
Basic Instrumentation Symbols | P&ID | PFD | Gaurav Singh Rajput
Basic Instrumentation Symbols | P&ID | PFD | Gaurav Singh RajputBasic Instrumentation Symbols | P&ID | PFD | Gaurav Singh Rajput
Basic Instrumentation Symbols | P&ID | PFD | Gaurav Singh Rajput
 
Présentation IIRB 2024 M.Campoverde R.Duval
Présentation IIRB 2024 M.Campoverde R.DuvalPrésentation IIRB 2024 M.Campoverde R.Duval
Présentation IIRB 2024 M.Campoverde R.Duval
 
Chapter 1 - Drilling Fluid Functions GR.ppt
Chapter 1 - Drilling Fluid Functions GR.pptChapter 1 - Drilling Fluid Functions GR.ppt
Chapter 1 - Drilling Fluid Functions GR.ppt
 
HB Self-Body characteristics UHV understanding
HB Self-Body characteristics UHV understandingHB Self-Body characteristics UHV understanding
HB Self-Body characteristics UHV understanding
 
Microservices: Benefits, drawbacks and are they for me?
Microservices: Benefits, drawbacks and are they for me?Microservices: Benefits, drawbacks and are they for me?
Microservices: Benefits, drawbacks and are they for me?
 
Chase Commerce Center History Nordberg manufacturing Rexnord Global power com...
Chase Commerce Center History Nordberg manufacturing Rexnord Global power com...Chase Commerce Center History Nordberg manufacturing Rexnord Global power com...
Chase Commerce Center History Nordberg manufacturing Rexnord Global power com...
 
Checklist to troubleshoot CD moisture profiles.docx
Checklist to troubleshoot CD moisture profiles.docxChecklist to troubleshoot CD moisture profiles.docx
Checklist to troubleshoot CD moisture profiles.docx
 
Model Approved Food/ sanitary Grade Flow Meter
Model Approved Food/ sanitary Grade Flow MeterModel Approved Food/ sanitary Grade Flow Meter
Model Approved Food/ sanitary Grade Flow Meter
 
B111_FTS_2011.06.01 Fuel Tank Safety.pdf
B111_FTS_2011.06.01 Fuel Tank Safety.pdfB111_FTS_2011.06.01 Fuel Tank Safety.pdf
B111_FTS_2011.06.01 Fuel Tank Safety.pdf
 
【文凭定制】坎特伯雷大学毕业证学历认证
【文凭定制】坎特伯雷大学毕业证学历认证【文凭定制】坎特伯雷大学毕业证学历认证
【文凭定制】坎特伯雷大学毕业证学历认证
 
Center Enamel is the leading bolted steel tanks manufacturer in China.docx
Center Enamel is the leading bolted steel tanks manufacturer in China.docxCenter Enamel is the leading bolted steel tanks manufacturer in China.docx
Center Enamel is the leading bolted steel tanks manufacturer in China.docx
 
Basic Concepts of Material Science for Electrical and Electronic Materials ...
Basic Concepts of Material Science for  Electrical and Electronic Materials  ...Basic Concepts of Material Science for  Electrical and Electronic Materials  ...
Basic Concepts of Material Science for Electrical and Electronic Materials ...
 
ChoiAccess.pptbuhuhujhhuhuhuhuhuhhhhhhhhhhhhh
ChoiAccess.pptbuhuhujhhuhuhuhuhuhhhhhhhhhhhhhChoiAccess.pptbuhuhujhhuhuhuhuhuhhhhhhhhhhhhh
ChoiAccess.pptbuhuhujhhuhuhuhuhuhhhhhhhhhhhhh
 
1 Energy Management for Lighting Systems.pptx
1 Energy Management for Lighting Systems.pptx1 Energy Management for Lighting Systems.pptx
1 Energy Management for Lighting Systems.pptx
 
21 SCHEME_21EC53_VTU_MODULE-4_COMPUTER COMMUNCATION NETWORK.pdf
21 SCHEME_21EC53_VTU_MODULE-4_COMPUTER COMMUNCATION NETWORK.pdf21 SCHEME_21EC53_VTU_MODULE-4_COMPUTER COMMUNCATION NETWORK.pdf
21 SCHEME_21EC53_VTU_MODULE-4_COMPUTER COMMUNCATION NETWORK.pdf
 

A Literature Review on Iris Segmentation Techniques for Iris Recognition Systems

  • 1. IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661, p- ISSN: 2278-8727Volume 11, Issue 1 (May. - Jun. 2013), PP 46-50 www.iosrjournals.org www.iosrjournals.org 46 | Page A Literature Review on Iris Segmentation Techniques for Iris Recognition Systems Ms. Sruthi.T.K 1, Ms. Jini.K.M 2 Post Graduate Scholar, Computer Science Department, Nehru college of Engineering, India1 Assistant Professor, Computer Science Department, Nehru College of Engineering, India 2 Abstract—A biometric system offers automatic identification of a human being based on the unique feature or characteristic which is being possessed by the individual. The iris segmentation has its own major applications in the field of surveillance as well as in security purposes. The performance of the iris recognition systems depends heavily on segmentation and normalization techniques. A review of various segmentation approaches used in iris recognition is done in this paper. The survey is represented in tabular form for quick reference. Index Terms—iris recognition, biometrics, iris segmentation I. Introduction In the recent years, drastic improvements have been accomplished in the areas like iris recognition, automated iris segmentation, edge detection, boundary detection etc. Iris recognition is a biometric recognition technology that utilizes the pattern recognition techniques based on the high quality images of iris.. An iris recognition system mainly uses infrared or else the visible light. The systems which are based on near infrared light (NIR) are very common because NIR will not generate reflections that makes iris recognition complex. But, NIR images lacks pigment coloration information, thus recognition algorithms must entirely depend on the patterns that are unrelated to color. Iris recognition which is based on visible light raise up pigmentation, thus the recognition systems will be able to exploit the color patterns, which make identification much easier. This is because, the pigmentation patterns contain a lots of information that can be utilized for recognition. But the visible light reflections in these types of systems can result in a extensive amount of noise in the gathered images. A typical iris recognition system consists of mainly three modules. They are image acquisition, pre- processing stage as well as feature extraction and encoding. Image acquisition is a module which involves the capturing of iris images with the help of sensors. Pre-processing module provides the determination of the boundary of iris within the eye image, and then extracts the iris portion from the image in order to facilitates its processing. It involves the stages like iris segmentation, iris normalization, image enhancement etc. The performance of the system has been analyzed in the feature extraction and encoding stage. All these stages involve their own developments. Major improvements have been made in the field of iris segmentation. In this paper, some of the methods involving iris segmentation have been analyzed. Approaches like Integrodifferential operator [1], Hough transform [2] constitute a major part in the iris recognition techniques. Many other iris recognition as well as the iris segmentation approaches [3,4,5,6,7,8] has been introduced. Each one has its own advantage as well as the disadvantage. Major drawbacks involved in all the papers is that, the segmentation accuracy has not been achieved yet. Thus, there is a strong need to develop a new segmentation approach that is more reliable as well as robust, which can automatically segment non ideal iris images, which has been acquired using visible illumination in very less constrained imaging environments. Thus, here a unified framework approach [9] has been introduced, which automatically provide the localized eye images from face images for iris recognition. And also, an efficient post processing operations has been introduced in order to mitigate the noisy pixels which have been formed by the misclassification. II. Approaches Used For Iris Recognition A. Integrodifferential operator This approach [1] is regarded as one of the most cited approach in the survey of iris recognition. Daugman uses an integrodifferential operator for segmenting the iris. It find both inner and the outer boundaries of the iris region. The outer as well as the inner boundaries are referred to as limbic and pupil boundaries. The parameters such as the center and radius of the circular boundaries are being searched in the three dimensional parametric space in order to maximize the evaluation functions involved in the the model. This algorithm achieves high performance in iris recognition. It is having a drawback that, it suffers from heavy computation.
  • 2. A Literature review on Iris Segmentation Techniques for Iris Recognition System www.iosrjournals.org 47 | Page B. Hough Transform In this paper, in order to perform personal identification and also the verification, an automated iris recognition system has been examined as the biometrically based technology. This paper also defines the technical issues which are being produced while designing an iris recognition system. The technical issues involve three parts viz. while image acquisition, iris localization and also matching of the extracted iris pattern. The major challenges involved in the image acquisition are in terms of image resolution and also in the focus using some standard optics. Here, an extant system has been used in order to provide a remedy to these challenges. Next issue is the iris localization. That is the image capture during the image acquisition will be a very larger image which contains iris as a part of it. Thus localization of the part that corresponds to the iris from acquired image is very much important. The edge detection has been performed through the gradient-based Canny edge detector, which is followed by the circular Hough transform [2], which is used for iris localization. The final issue is the pattern matching. After the localization of the region of the acquired image which corresponds to the iris, the final operation is to decide whether pattern matches with the previously saved iris pattern. This stage involves alignment, representation, goodness of match and also the decision. All these pattern matching approaches relies mainly on the method which are closely coupled to the recorded image intensities. If there occurs a greater variation in any one of the iris, one way to deal with this is the extraction as well as matching the sets of features that are estimated to be more vigorous to both photometric as well as geometric distortions in the obtained images. The advantage of this method is that it provides segmentation accuracy up to an extent. The drawback of this approach is that, it does not provide any attention to eyelid localization (EL), reflections, eyelashes, and shadows. C. Masek Method Masek introduced an open iris recognition system [3] for the verification of human iris uniqueness and also its performance as the biometrics. The iris recognition system consists of an automated segmentation system, which localise the iris region from an eye image and also isolate the eyelid, eyelash as well as the reflection regions. This Automatic segmentation was achieved through the utilization of the circular Hough transform in order to localise the iris as well as the pupil regions, and the linear Hough transform has been used for localising the eyelid occlusion. Thresholding has been employed for isolating the eyelashes as well as the reflections. Now, the segmented iris region has got normalized in order to eliminate the dimensional inconsistencies between the iris regions. This was achieved by applying a version of Daugman’s rubber sheet model, in which the iris is modeled as a flexible rubber sheet, which is unpacked into a rectangular block with constant polar dimensions. Ultimately, the iris features were encoded by convolving the normalized iris region with the 1D Log-Gabor filters and phase quantizing the output to produce a bit-wise biometric template. For metric matching, the Hamming distance has been chosen, which provides a measure of number of disagreed bits between two templates. The drawback of [2] has been recovered in this paper i.e., the localisation of the circular iris as well as the pupil region, occlusion of eyelids as well as the eyelashes, and also the reflection occurs. The drawback of this approach is that the iris segmentation is not that much accurate and also the speed of the system is low. D. Fuzzy clustering algorithm A new iris segmentation approach, which has a robust performance in the attendance of heterogeneous as well as noisy images, has been developed in this. The process starts with the image-feature extraction where three discrete i.e., (x, y) which corresponds to the pixel position, and z which corresponds to its intensity values has got extracted for each and every image pixel, which is followed by the application of a clustering algorithm which is the fuzzy K-means algorithm[4]. This has been used inorder to classify each and every pixel and then generate the intermediate image. This correspondent image is then used by the edge-detector algorithm. As it has additional homogeneous characteristics, this eases the tuning of the parameters which were needed by the edge-detector algorithm. The main advantage of this method is that, it provides a better segmentation for non co- operative iris recognition. The major drawback in this method is that thorough (extensive) search is needed in order to recognize the circle parameters of both the pupil as well as the iris boundaries. E. Pulling and Pushing (PP) Method A perfect (accurate) as well as a rapid iris segmentation algorithm for iris biometrics has been developed in this. There are mainly five major contributions in this. Firstly, a novel reflection removal method has been developed in order to exclude the specularities involved in the input images, also an Adaboost-cascade iris detector has been used in order to detect the iris in them and also to exclude the non iris image parts before further processing such that redundant computations can be avoided. In addition to this, a rough iris center has been extracted in the iris images. Second contribution is that, beginning from the rough iris center, a novel puling and pushing (PP) [5] procedure has been developed in order to accurately localize the circular iris
  • 3. A Literature review on Iris Segmentation Techniques for Iris Recognition System www.iosrjournals.org 48 | Page boundaries. The PP method directly finds the shortest path to the valid parameters. Third is that, a cubic smoothing spline has been adopted in order to deal with the noncircular iris boundaries. Fourth contribution is that, an efficient method for the localization of the eyelids has been developed. The main difficulties of eyelid localization difficulties such as sharp irregularity of eyelids as well as the noise due to the eyelashes has been addressed proficiently by a rank filter and also a histogram filter. Finally, the eyelashes as well as the shadows have been detected with statistically learned prediction model. The advantage of PP method is the accuracy and speed. The drawback of this method is that the occurrence of the segmentation error. F. Eight-neighbor connection based clustering An efficient as well as robust algorithm for noisy iris image segmentation in the background of non cooperative and less-cooperative iris recognition has been developed in this. The major contributions involved in this are as follows. Firstly, a novel region growing scheme known as the eight-neighbor connection based clustering [6] has been proposed in order to cluster the whole iris image into different parts. Then, genuine iris region has been extracted with the aid of several semantic priors, and also the non-iris regions such as eyelashes, eyebrow, glass frame, hair, etc are identified and also excluded as well, which intensely reduces the possibility of mis localizations occurring on the non-iris regions. Secondly, an integrodifferential constellation has been introduced inorder to accelerate the traditional integrodifferential operator, and then, enhance its global convergence ability for pupillary as well as the limbic boundary localization. Thirdly, a 1-D horizontal rank filter as well as an eyelid curvature model has been adopted in order to tackle the eyelashes as well as the shape irregularity, during eyelid localization. Finally, the eyelash as well as the shadow occlusions has been detected with the aid of learned prediction model which is based on the intensity statistics between different iris regions. The advantage of this method is that the iris segmentation accuracy has been attained. The drawback is segmentation of noisy iris images should be improved. G. Segmentation approach based on Fourier spectral density A new segmentation method for noisy frontal view iris images which is captured with minimum cooperation based on the Fourier spectral density [7] has been proposed in this paper. This approach computes the Fourier spectral density for each pixel with the aid of its neighborhood and then executes row-wise adaptive thresholding, and thus results in a binary image which gives the iris region in a fairly accurate manner. This segmentation method can also be used in order to calculate limbic as well as the pupil boundaries. This is having the advantage that, this has lower computations as compared to that of [1], [2]. The drawback is that, limbic boundary detection should be improved. H. Circular Gabor Filter Segmentation of iris is one of the most vital as well as difficult task in iris recognition. [1] and [2] are widely used for iris texture segmentation. But their computational time consumption is high. Time consumption is mainly required in order to recognize the initial centers of both iris as well as pupil circular boundaries. A simple solution for this problem has been given in this paper. The circular Gabor filter (CGF) [8] has been utilized in order to localize the initial pupil center. The main advantage of this approach is that the segmentation accuracy for both the pupil as well as the iris boundaries has been achieved. The drawback is that, the overall segmentation accuracy is less than that of [9]. All these techniques have improved the performance of the iris recognition system. All these techniques acquire segmentation accuracy in many areas such as boundary detection, iris detection, pupil and limbic boundary detection etc. But none of these papers provide a solution for attaining overall segmentation accuracy. Thus there is a an extreme need for developing a new segmentation method, which are more reliable as well as robust for automatically segmenting the non ideal iris images. This paper introduces a unified solution for iris segmentation [9]. Here, a new iris segmentation framework has been developed, which can robustly segment the iris images attained using NIR or else the visible illumination. This approach exploits multiple higher order local pixel dependencies using Zernike moments (ZM), in order to strongly (robustly) classify the eye region pixels into iris or else the non iris regions using trained neural network/ support vector machine (NN/SVM) classifiers. Image enhancement using single scale retinex (SSR) algorithm has been employed for illumination variation problem. Face as well as the eye detection modules has been integrated in the unified framework to automatically provide the localized eye region from facial image for segmenting the iris. A robust post processing operations algorithm has been developed inorder to effectively alleviate the noisy pixels which has been caused due to misclassification.
  • 4. A Literature review on Iris Segmentation Techniques for Iris Recognition System www.iosrjournals.org 49 | Page Table1: Comparison table on literature survey III. Conclusion This paper presents a literature survey on the various segmentation techniques involved in iris recognition. There are various techniques that can be used for this purpose. Overall segmentation accuracy of all these techniques has been analyzed. Higher the segmentation rate, thus higher is its performance The unified framework has the highest segmentation rate and also has highest performance. NAME METHOD PERFORMANCE DISADVANTAGES High confidence visual recognition of persons by a test of statistical independence Integrodifferential operator High performance in iris recognition Computational time is very high Iris Recognition: An emerging biometric technology Hough transform Segmentation accuracy achieved up to an extent Does not provide attention to EL as well as reflections etc Recognition of Human Iris Patterns for Biometric Identification Liber Masek’s encoding algorithm Localization of circular iris region as well as eyelids, eyelashes and also the reflections occurs Speed of the system is low Iris segmentation methodology for non cooperative recognition Fuzzy clustering algorithm Better segmentation for non co-operative iris recognition Thorough search is needed to recognize the circle parameters of both pupil and iris boundaries Toward Accurate and Fast Iris Segmentation for Iris Biometrics Pushing and pulling (PP) method Possess accuracy and speed Occurrence of segmentation error Efficient and robust segmentation of noisy iris images for non cooperative iris recognition Eight-neighbor connection based clustering iris segmentation accuracy has been attained to an extent segmentation of noisy iris images should be improved Efficient segmentation technique for noisy frontal view iris images using Fourier spectral density Segmentation approach based on Fourier spectral density Computational complexity is low Limbic boundary detection should be improved. Iris Segmentation in Visible Wavelength Environment Circular Gabor Filter segmentation accuracy for both the pupil as well as the iris boundaries has been achieved Over all segmentation accuracy is less than that of the unified framework approach
  • 5. A Literature review on Iris Segmentation Techniques for Iris Recognition System www.iosrjournals.org 50 | Page References [1] J.G. Daugman, High confidence visual recognition of persons by a test of statistical independence, IEEE Transactions on Pattern Analysis and Machine Intelligence, 15, p.1148, Nov 1993 [2] R.P. Wildes, Iris recognition: An emerging biometric technology, Proceedings of the IEEE, 85 p.1348, sep. 1997 [3] L. Masek, ―Recognition of Human Iris Patterns for Biometric Identification‖, M.S. Dissertation, the University of Western Australia, 2003 [4] H. Proença, L.A. Alexandre, ―Iris segmentation methodology for non-cooperative recognition‖, IEE Proceedings of Vision, Image and Signal Processing, pp. 199-205, 2006 [5] Z. He, T. Tan, Z. Sun, and X. Qiu, ―Toward accurate and fast iris segmentation for iris biometrics,‖ IEEE Trans. Pattern Anal. Machine Intelligence, vol. 31, no. 9, pp. 1670–1684, Sep. 2009. [6] T. Tan, Z. He, and Z. Sun, ―Efficient and robust segmentation of noisy iris images for non-cooperative iris recognition,‖ Image Vis. Comput., vol. 28, no. 2, pp. 223–230, Feb. 2010. [7] N.B. Puhan, N. Sudha, A. Sivaraman Kaushalram, Efficient segmentation technique for noisy frontal view iris images using Fourier spectral density, Signal, Image and Video Processing, 5, p. 105, 2011. [8] Radman, A., Jumari, K., and Zainal, N, Iris segmentation in visible wavelength environment. Procedia Engineering, 41:743–748, 2012 [9] Tan, C. and Kumar, A., Unified framework for automated iris segmentation using distantly acquired face images. IEEE Transactions on Image Processing, 21(9):4068–4079, S