Texture feature extraction and classification for iris diagnosis

Authors:
Lin Ma;Naimin Li
Affiliations:
School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China;School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China
Venue:
ICMB'08 Proceedings of the 1st international conference on Medical biometrics
Year:
2008

Citing 3
Cited 0

Texture Segmentation Using Fractal Dimension

IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical Richness of Visual Phase Information: Update on Recognizing Persons by Iris Patterns

International Journal of Computer Vision
High Confidence Visual Recognition of Persons by a Test of Statistical Independence

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Appling computer aided techniques in iris image processing, and combining occidental iridology with the traditional Chinese medicine is a challenging research area in digital image processing and artificial intelligence. This paper proposes an iridology model that consists the iris image pre-processing, texture feature analysis and disease classification. To the pre-processing, a 2-step iris localization approach is proposed; a 2-D Gabor filter based texture analysis and a texture fractal dimension estimation method are proposed for pathological feature extraction; and at last support vector machines are constructed to recognize 2 typical diseases such as the alimentary canal disease and the nerve system disease. Experimental results show that the proposed iridology diagnosis model is quite effective and promising for medical diagnosis and health surveillance for both hospital and public use.