Elimination of Iris Hazards Intended for Localization Using Visible Features of Iris Region

Abstract Iris features provides a unique biometric identification in the eye. The uniqueness is maintained for left and right eye, twins. Even during the eye transportation, the natures of iris parameters are varied by nature. The eye lids, lashes and flash light impressions are the crucial hazards, during the localization of iris region. The proposed method is used to detect the iris boundary, by eliminating the hazards. The eye image is pre-processed by using the filter with suitable coefficients. The flash image is eliminated in the pre-processing stage. The morphological operation is imposed on the pre-processed image, which results the exact pupil area. The edge detection technique is applied to find the visible iris region, either on the left or right side. The radius is calculated from the pupil centre to the iris visible boundary. The circle is formed on the iris region, which exactly fits on iris boundary. The iris region curve formed over the eye lashes and eye lids. The proposed method is tested with CASIA Ver3.0 image, which eliminates the iris hazards to identify the unique radius as a feature in the eye image.

[1]  Eri Prasetyo Wibowo,et al.  Real-Time Iris Recognition System Using a Proposed Method , 2009, 2009 International Conference on Signal Processing Systems.

[2]  Topi Mäenpää An Iterative Algorithm for Fast Iris Detection , 2005, IWBRS.

[3]  Rafael C. González,et al.  Digital image processing using MATLAB , 2006 .

[4]  Tusheng Lin,et al.  Detection of Non-iris Region in the Iris Recognition , 2008, 2008 International Symposium on Computer Science and Computational Technology.

[5]  Manesh Kokare,et al.  Iris Recognition Using Discrete Wavelet Transform , 2009, 2009 International Conference on Digital Image Processing.

[6]  S. Thainimit,et al.  An Iris Verification Using Edge Detection , 2005, 2005 5th International Conference on Information Communications & Signal Processing.

[7]  Hironobu Takano,et al.  Iris detection method using particle filter and edge directional features , 2010, 2010 World Automation Congress.

[8]  Libor Masek,et al.  Recognition of Human Iris Patterns for Biometric Identification , 2003 .

[9]  Matti Pietikäinen,et al.  Adaptive document image binarization , 2000, Pattern Recognit..