Improved Daugman’s Method

Team Beta

Bryan Chamberlain

Kyle Barkes

Daniel Lohmer

Patrick Braga-Henebry

CSE30332 Programming Paradigms

Professor Patrick Flynn

Outline

• Problem statement

• Literature Review

• Selected Technique

• Implementation Details

• Experimental Results

• Conclusions and Comments

Problem Statement

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

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)

other paper...

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

• 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

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

Pupilic LocalizationL= DC

5−2∗DC−128

128

L= DC

5−2∗DC−x

y

DC=204, L=83 : y=166204−x 211

DC=156, L=56 : y=112204−x 124

L= DC

5−2∗DC168

293

• 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 = -168 y = 293

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

r= A/

• The integro-differential operator is then used for fine-localization

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):

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)

Fine

• Searches around coarse (x,y,r) for better fit

Experiments

• Describe data set and their size

• Provide measure allows evaluation of the quality of the results.

• Include table that summarizes the results

Experiment Data

• Put a table here...

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