This paper presents a new approach for personal authentication using a lossless watermarking technique based on hand images features. The proposed method attempts to embed personal message to the hand image, which will not destroy the original hand images and can improve the recognition rate and the recognition speed of palmprint-based verification system. We could extract the watermark from the hand images for the coarse-level identification, and then make the fine-lever identification according to the content of the watermark. Our experiments on an image database of 100 users achieve results and suggest that the matching scores can achieve better performance in contrast to conventional approaches.
Published in:
Wavelet Analysis and Pattern Recognition, 2007. ICWAPR '07. International Conference on
(Volume:4
)
Date of Conference: 2-4 Nov. 2007