Improved Daugman’s Method

16
Improved Daugman’s Method Team Beta Bryan Chamberlain Kyle Barkes Daniel Lohmer Patrick Braga-Henebry CSE30332 Programming Paradigms Professor Patrick Flynn

description

Team Beta Bryan Chamberlain Kyle Barkes Daniel Lohmer Patrick Braga-Henebry CSE30332 Programming Paradigms Professor Patrick Flynn. Improved Daugman’s Method. Outline. Problem statement Literature Review Selected Technique Implementation Details Experimental Results - PowerPoint PPT Presentation

Transcript of Improved Daugman’s Method

Page 1: Improved Daugman’s Method

Improved Daugman’s Method

Team Beta

Bryan Chamberlain

Kyle Barkes

Daniel Lohmer

Patrick Braga-Henebry

CSE30332 Programming Paradigms

Professor Patrick Flynn

Page 2: Improved Daugman’s Method

Outline

• Problem statement

• Literature Review

• Selected Technique

• Implementation Details

• Experimental Results

• Conclusions and Comments

Page 3: Improved Daugman’s Method

Problem Statement

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

Page 4: Improved Daugman’s Method

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)

Page 5: Improved Daugman’s Method

other paper...

Page 6: Improved Daugman’s Method

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

Page 7: Improved Daugman’s Method

• 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

Page 8: Improved Daugman’s Method

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

Page 9: Improved Daugman’s Method

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

Page 10: Improved Daugman’s Method

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

Page 11: Improved Daugman’s Method

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):

Page 12: Improved Daugman’s Method

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)

Page 13: Improved Daugman’s Method

Fine

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

Page 14: Improved Daugman’s Method

Experiments

• Describe data set and their size

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

• Include table that summarizes the results

Page 15: Improved Daugman’s Method

Experiment Data

• Put a table here...

Page 16: Improved Daugman’s Method

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