Texture Feature Extraction and Classification for Iris Diagnosis

  • Lin Ma
  • Naimin Li
Conference paper

DOI: 10.1007/978-3-540-77413-6_22

Part of the Lecture Notes in Computer Science book series (LNCS, volume 4901)
Cite this paper as:
Ma L., Li N. (2007) Texture Feature Extraction and Classification for Iris Diagnosis. In: Zhang D. (eds) Medical Biometrics. ICMB 2008. Lecture Notes in Computer Science, vol 4901. Springer, Berlin, Heidelberg

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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Lin Ma
    • 1
  • Naimin Li
    • 1
  1. 1.School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang 150001China

Personalised recommendations