Paper
8 May 2012 Parallel computing-based sclera recognition for human identification
Yong Lin, Eliza Y. Du, Zhi Zhou
Author Affiliations +
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.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yong Lin, Eliza Y. Du, and Zhi Zhou "Parallel computing-based sclera recognition for human identification", Proc. SPIE 8406, Mobile Multimedia/Image Processing, Security, and Applications 2012, 840603 (8 May 2012); https://doi.org/10.1117/12.918166
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Sclera

Image segmentation

Detection and tracking algorithms

Iris recognition

Algorithm development

Databases

Image registration

RELATED CONTENT

Multimodal eye recognition
Proceedings of SPIE (April 28 2010)
Challenging ocular image recognition
Proceedings of SPIE (May 17 2011)
A new approach for sclera vein recognition
Proceedings of SPIE (April 28 2010)

Back to Top