1. Improved Daugman’s Method Team Beta Bryan Chamberlain Kyle Barkes Daniel Lohmer Patrick Braga-Henebry CSE30332 Programming Paradigms Professor Patrick Flynn

2. Outline Problem statement Literature Review Selected Technique Implementation Details Experimental Results Conclusions and Comments

3. Problem Statement Our team sought to create an efficient iris localization algorithm through both research and self-testing.

4. Literature Review How Iris Recognition Works (John Daugman)‏ Image understanding for iris biometrics: A survey (Kevin W. Bowyer, Karen Hollingsworth, Patrick J. Flynn)‏ An Improved Method for Daugman's Iris Localization Algorithm (Xinying Ren, Zhiyong Peng, Qinging Zeng, Chaonan Peng, Jianhua Zhang, Shuicai Wu, Yanjun Zeng)‏ Efficient Iris Recognition through Improvement of Feature Vector and Classifier (Shinyoung Lim, Kwanyong Lee, Okhwan Byeon, and Taiyun Kim)‏ Iris recognition: An emerging biometric technology (Richard P. Wildes)‏ Iris segmentation methodology for non-cooperative recognition (Hugo Proença, Luís A, Alexandre)‏

5. other paper...

6. An Improved Method for Daugman's Iris Localization Algorithm Localization of pupillary boundary –Coarse, then fine Localization of limbus boundary –Coarse, then fine, based on right and left canthus Localization of upper and lower eyelid boundaries –excludes area most likely to be noise

7. With pupil boundary detection: –Ability to set accurate threshold value With limbus boundary detection: –Noise getting in the way of edge detection on either side of the eye With eyelid localization: –Loss of valid data –Inability to detect extreme rotation Concerns

8. Implementation Utilized: Python, OpenCV, Google Code, SVN Pupil –Coarse and Fine wrapped in one Limbus –Coarse –Fine Main –Combines all functions –A variety of output options

9. Pupilic Localization Threshold as defined in paper: 128 proved to be a bad value Solved for new values x and y: With a high average gray value(DC): With a low average gray value(DC): Solved for new threshold equation: x = -168y = 293

10. Pupilic Localization Cont'd Compare each pixel, to threshold value If I(x,y) < L, then it is considered to be in the pupil Radius is determined using the number of pixels found and the area of a circle Center coordinates are found by calculating the average x and y values of every pixel The integro-differential operator is then used for fine-localization

11. Integro-differential operator def max_circ_diff(src, x0, y0, rmin = 0, rmax = 200, d_r = 9, theta_min = 0, theta_max = 2*pi, theta_steps = 24, debug = 0):

12. Coarse Limbic Uses pupilic (x,y,r) to find limbic for L/R arcs Increments radius, keeps max(IDO)‏ Averages L/R (x,y,r)‏

13. Fine Searches around coarse (x,y,r) for better fit

14. Experiments Describe data set and their size Provide measure allows evaluation of the quality of the results. Include table that summarizes the results

15. Experiment Data Put a table here...

16. Conclusions and comments Assess overall work Discuss lessons learned Do Differently? OO, C++ What worked well? –Integro-differential operator –Threshold evaluator What didn’t work well? –Delta(intensity) check on pupil coarse