A Statistical Approach for Iris Recognition Using K-NN Classifier

Full Text (PDF, 381KB), PP.46-52

Views: 0 Downloads: 0


Dolly Choudhary 1,* Ajay Kumar Singh 1 Shamik Tiwari 1

1. Deptt. Of Computer Sc. & Engineering Faculty of Engineering & Tech., MITS Laxmangarh (India)

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2013.04.06

Received: 13 Dec. 2012 / Revised: 24 Jan. 2013 / Accepted: 28 Feb. 2013 / Published: 8 Apr. 2013

Index Terms

Iris recognition, Texture feature, K-NN, Hough transform


Irish recognition has always been an attractive goal for researchers. The identification of the person based on iris recognition is very popular due to the uniqueness of the pattern of iris. Although a number of methods for iris recognition have been proposed by many researchers in the last few years. This paper proposes statistical texture feature based iris matching method for recognition using K-NN classifier. Statistical texture measures such as mean, standard deviation, entropy, skewness etc., and six features are computed of normalized iris image. K-NN classifier matches the input iris with the trained iris images by calculating the Euclidean distance between two irises. The performance of the system is evaluated on 500 iris images, which gives good classification accuracy with reduced FAR/FRR.

Cite This Paper

Dolly Choudhary,Ajay Kumar Singh,Shamik Tiwari,"A Statistical Approach for Iris Recognition Using K-NN Classifier", IJIGSP, vol.5, no.4, pp.46-52, 2013. DOI: 10.5815/ijigsp.2013.04.06


[1]Sudipta Roy, Abhijit Biswas, A Personal Biometric Identification Technique based on Iris Recognition, (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 2 (4) , pp. 1474- 1477 , 2011.

[2]Basit, M. Y. Javed, M. A. Anjum, Efficient Iris Recognition Method for Human Identification, World Academy of Science, Engineering and Technology 4, 2005.

[3]H. Huifang, and H. Guangshu, "Iris Recognition based on Adjustable Scale Wavelet Transform" in Proc. IEEE, 2005.

[4]Suresh, K. L. Shunmuganathan, "Image Texture Classification using Gray Level Co-Occurrence Matrix Based Statistical Features", European Journal of Scientific Research ISSN 1450-216X Vol.75 No.4 (2012), pp. 591-597.

[5]Ajay Kumar Singh, Shamik Twari and V P Shukla, "Wavelet based multi class image classification using neural network", International Journal of Computer Applications Volume 37 - Number 4 Year of Publication: 2012

[6]Fix, and J. Hodges, "Discriminatory analysis. Nonparametric discrimination: Consistency properties". Technical Report 4, USAF School of Aviation Medicine, Randolph Field, Texas, 1951. 

[7]T.M. Cover, and P.E. Hart, "Nearest neighbor pattern classification", IEEE Transactions on Information Theory, 13, pp. 21–27, 1967. 

[8]R.O. Duda, and P.E. Hart, Pattern classification and scene analysis, New York: Wiley, 1973

[9]W. Kong, D. Zhang. Accurate iris segmentation based on novel reflection and eyelash detection model. Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, Hong Kong, 2001.

[10]S. Sanderson, J. Erbetta. Authentication for secure environments based on iris scanning technology. IEE Colloquium on Visual Biometrics, 2000.

[11]Alavanis L K., Mougiakakou S.G., Nikita A. And Nikita K.S., "Evaluation of Texture Features in Hepatic Tissue Charateriztion from non Enhanced CT images", Proceedings of the twenty ninth annual internation conference of the IEEE Engineering in Medicine and Biology Society, Lyon, pp 3741-3744.

[12]Belur V. Dasarathy, "Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques", McGraw-Hill Computer Science Series, IEEE Computer Society Press, Las Alamitos, California, pp. 217-224, 1991. 

[13]Y. Lihua, D. Qi, and G. Yanjun, "Study on KNN Text Categorization Algorithm", Micro Computer Information, 21, pp. 269-271, 2006.

[14]Casia-irisv2, institute of Automation, Chinese Academy of Sciences, http://www.cbsr.ia.ac.cn/IrisData.