Share Email Print

Proceedings Paper

Parallel computing-based sclera recognition for human identification
Author(s): Yong Lin; Eliza Y. Du; Zhi Zhou
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Compared to iris recognition, sclera recognition which uses line descriptor can achieve comparable recognition accuracy in visible wavelengths. However, this method is too time-consuming to be implemented in a real-time system. In this paper, we propose a GPU-based parallel computing approach to reduce the sclera recognition time. We define a new descriptor in which the information of KD tree structure and sclera edge are added. Registration and matching task is divided into subtasks in various sizes according to their computation complexities. Every affine transform parameters are generated by searching on KD tree. Texture memory, constant memory, and shared memory are used to store templates and transform matrixes. The experiment results show that the proposed method executed on GPU can dramatically improve the sclera matching speed in hundreds of times without accuracy decreasing.

Paper Details

Date Published: 8 May 2012
PDF: 10 pages
Proc. SPIE 8406, Mobile Multimedia/Image Processing, Security, and Applications 2012, 840603 (8 May 2012); doi: 10.1117/12.918166
Show Author Affiliations
Yong Lin, Indiana Univ.-Purdue Univ. (United States)
Xidian Univ. (China)
Ningxia Normal Univ. (China)
Eliza Y. Du, Indiana Univ.-Purdue Univ. (United States)
Zhi Zhou, Indiana Univ.-Purdue Univ. (United States)

Published in SPIE Proceedings Vol. 8406:
Mobile Multimedia/Image Processing, Security, and Applications 2012
Sos S. Agaian; Sabah A. Jassim; Eliza Yingzi Du, Editor(s)

© SPIE. Terms of Use
Back to Top