AN APPEARANCE-BASED METHOD FOR IRIS DETECTION

Biometrics has received much attention in the current society and iris recognition is very attractive for its high reliability and non-invasiveness. Iris detection plays an important role in the subsequent processing of a real iris recognition system. Both the accuracy and speed of iris detection are crucial. In this paper, we propose an appearance-based algorithm for iris detection. It includes the following three steps. First, the method detects whether there is a pupil in the image using the Support Vector Machine (SVM). Then, 12 sample vectors are selected along the radial direction from the center of the pupil to determine whether the structure outside the pupil is like an iris using the Linear Discriminant Analysis (LDA). Finally, we make a decision by fusing the above two results. Extensive experimental results show that the method has a promising performance with the accuracy of more than 97%.

[1]  Okhwan Byeon,et al.  Efficient Iris Recognition through Improvement of Feature Vector and Classifier , 2001 .

[2]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[3]  E. Mayoraz,et al.  Fusion of face and speech data for person identity verification , 1999, IEEE Trans. Neural Networks.

[4]  Thorsten Joachims.  A Statistical Learning Model of Text Classification for SVMs , 2002 .

[5]  John Daugman,et al.  High Confidence Visual Recognition of Persons by a Test of Statistical Independence , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Richard P. Wildes,et al.  A machine-vision system for iris recognition , 2005, Machine Vision and Applications.

[7]  Lionel Torres,et al.  Person Identification Technique Using Human Iris Recognition , 2002 .

[8]  Avinash C. Kak,et al.  PCA versus LDA , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Carmen Sánchez Ávila,et al.  Iris Recognition with Low Template Size , 2001, AVBPA.

[10]  Dustin Boswell,et al.  Introduction to Support Vector Machines , 2002 .

[11]  Narendra Ahuja,et al.  Detecting Faces in Images: A Survey , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Boualem Boashash,et al.  A human identification technique using images of the iris and wavelet transform , 1998, IEEE Trans. Signal Process..

[13]  Sven Loncaric,et al.  A survey of shape analysis techniques , 1998, Pattern Recognit..

[14]  John Daugman,et al.  Statistical Richness of Visual Phase Information: Update on Recognizing Persons by Iris Patterns , 2001, International Journal of Computer Vision.

[15]  Tieniu Tan,et al.  Biometric personal identification based on iris patterns , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[16]  James L. Wayman,et al.  Fundamentals of Biometric Authentication Technologies , 2001, Int. J. Image Graph..

[17]  Tieniu Tan,et al.  Iris recognition using circular symmetric filters , 2002, Object recognition supported by user interaction for service robots.

[18]  John Daugman,et al.  The importance of being random: statistical principles of iris recognition , 2003, Pattern Recognit..