Biometric is the measurement and statistical analysis of human body characteristics. Biometric recognition is the use of
biological measurements of an individual for identification purposes. Iris recognition system include image acquisition, Segmentation,
normalization, features extraction, encoding and classification. Iris images are downloaded from CASIA Iris V1.0 database. Canny edge
detection is used to detect the edges of the eye image. Hough Transform is used to separate the iris region from the eye image. Also to
localize circular iris and pupil region of eye image, a circular Hough transform is used. Normalization technique convert the polar
coordinated into Cartesian coordinates. These Normalized image is used for feature extraction. Feature extraction is performed by
convolving the normalized iris region with Gabor wavelet, GLCM, etc. Depend on different features selection methods, find the feature
set. Finally to classify the eye images using SVM and ANN classifiers depends on features extracted from the database images.
Published In:IJCSN Journal Volume 6, Issue 3
Date of Publication : June 2017
Pages : 325-331
Figures :08
Tables : 01
Anupama B.L : received the B.Tech degree in Computer Science
and Engineering from Calicut University, Kerala, India, in 2015, and
currently doing M.Tech in Cyber Security in MET’S School of
Engineering,Mala - Abdul Kalam Technological University , Kerala,
India.
Asha Paul : is an Assistant Professor in MET’S School of
Engineering Mala, Thrissur, Kerala. Received B.Tech degree in
Information Technology from East Pont College of Engineering,
Bangalore and M.Tech from Karunya University, Coimbatore. She
has more than 3 years of teaching experience. Subject of interest
are Data Structures, \computer Organization and Design, Object
Oriented Programming, C Programming and Digital Data
Communication. She has presented paper on International
Conferences.
Sanaj M.S : is an Associate Professor in MET’S School of
Engineering Mala, Thrissur, Kerala. Received B.Tech degree from
CUSAT .and M.Tech from MS University Tirunelveli, Tamil Nadu. He
has more than 4 years of teaching experience. He has presented
paper on International Conferences.
Dr. D. Loganathan : is a Professor and Head of Computer Science
and Engineering department in MET’S School of Engineering, Mala,
Trissur, Kerala. After his B.E., and M.E degree, he accomplished a
doctoral degree from Anna University, Chennai, India. He has more
than 20 years of teaching experience and having 8 years of
research experience in engineering field. His research interest
includes Wireless Communication, Wireless Ad hoc Networks and
Image Processing. He has published several research papers in
various international journals.
CASIA, GLCM, SVM, ANN
An efficient classifier using iris code for gender prediction
is performed. CASIA version 1 eye image database is used
in the experiment. CASIA v1 eye image database contains
756 eye images from 108 individuals. Iris recognition
system consists of image acquisition, Segmentation,
normalization, features extraction, encoding and
classification. Canny edge detection is used to detect the
edges of the eye image. Hough Transform is used to
separate the iris region from the eye image. SVM gives the
classification rate of 90.25%. On other hand, ANN use back
propagation neural network for classification of iris
patterns. The training data for ANN is same as SVM and
the target has to give to the ANN. ANN gives the accuracy
rate of 83.65% for classification.
[1] J. E. Tapia and C. A. Perez, Kevin W. Bowyer “Gender
Classification From the Same Iris Code Used for
Recognition,” IEEE Transactions On Information
Forensics And Security, Vol. 11, No. 8, August 2016 .
[2] J. E. Tapia, C. A. Perez, and K. W. Bowyer, “Gender
classification from iris images using fusion of uniform
local binary patterns,” in Proc. Eur. Conf. Computing. Vis.,
Soft Biometrics Workshop (ECCV), 2014, pp. 751–763.
[3] B. Son, H. Won, G. Kee and Y. Lee, „„Discriminant Iris
Feature and Support Vector Machines for Iris
Recognition??, International Conference on Image
Processing, 2004.
[4] John Daugman. How iris recognition works. In Image
Processing. 2002. Proceedings.2002 International
Conference on, volume 1, pages I36, 2002.
[5] Zeng J, Liu ZQ. Type-2 fuzzy hidden Markov models to
phoneme recognition, Proceedings of the International
Conference on Pattern Recognition (ICRP), Cambridge
2004: 192-195.
[6] Hideyuki Tamura, Shunji Mori, and Takashi Yamawaki,”
Textural Features Corresponding to Visual Perception”
IEE transactions on systems. Man, and cybernetics, vol.
Smc-8, no. 6 June 1978.
[7] N. Cristianini, T. D. Shawe, “An Introduction to Support
Vector Machines and other Kernel-based Learning
Methods”, Cambridge University press, Cambridge
(2000).
[8] Namitha Shajan & Dr.D.Loganathan 2016, ‘Edge
Preserving Decomposition-Based Haze Removal in Video
Sequence Using Koschmiedars Law’ International Journal
of Computer Science and Information Technologies, Vol.
7 (3) , pp 1263-1266
[9] J. Daugman, “High confidence visual recognition of
persons by a test f statistical independence”, IEEE Trans.
Pattern Analysis and Machine Intelligence, vol. 15, pp.
1148- 1161, 1993.
[10] C. J. C. Burges, “A tutorial on support vector machines for
pattern recognition”. Data Mining and Knowledge
Discovery 2(2), 121-167 (1998). [11] Rahib H. Abiyev and Koray Altunkaya, “Personal Iris
Recognition Using Neural Network” ,International Journal
of Security and its Applications, vol. 2, no. 2, April, 2008.