Quick Search Adv. Search

J4

• article • Previous Articles     Next Articles

Using multi-matching system based on a simplified deformable model of the human iris for iris recognition

MING Xing 1, XU Tao 2, WANG Zheng-xuan 3   

  1. 1. College of Computer Science and Technology, Nanling Campus,Jilin University, 5988 Renmin Street,Changchun 130022, P. R. China;
    2. College of Mechanical Science and Engineering, Nanling Campus,Jilin University, 5988 Renmin Street, Changchun 130022, P. R. China;
    3. College of Computer Science and Technology, Qianwei Campus,Jilin University, 10 Qianwei Road, Changchun 130012, P. R. China.
  • Received:1900-01-01 Revised:1900-01-01 Online:2004-09-30 Published:1900-01-01
  • Contact: MING Xing

Abstract: A new method for iris recognition using a multi-matching system based on a simplified deformable model of the human iris was proposed. The method defined iris feature points and formed the feature space based on a wavelet transform. In the matching stage it worked in a crude manner. Driven by a simplified deformable iris model, the crude matching was refined. By means of such multi-matching system, the task of iris recognition was accomplished. This process can preserve the elastic deformation between an input iris image and a template and improve precision for iris recognition. The experimental results indicate the va-lidity of this method.

Key words: iris recognition, wavelet transform, feature points, deformable model