期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：7
出版社：S.S. Mishra
摘要：this paper discusses about multimodal biometric systems using two biometric traits (Face and Palm Print) and three biometric traits (Face, Fingerprint and Palm Print). The results from both the systems are compared and it is proved that system with three traits is more secure and reliable as compared to the system with two traits. This concept can be generalized for a multimodal system with n biometric traits. Major emphasis in the work is given on wavelet decomposition of the images of the traits, fusion of the images and feature extractor algorithm SIFT. The proposed method for evidence fusion is presented which is based on the image decomposition into multiple channels depending on their local frequency. The wavelet transform provides a framework to decompose image into a number of new images, each of them having a different degree of resolution. The wavelet based image fusion would be applied to two dimensional multispectral face, palmprint and fingerprint images. When the fused image is ready for further processing SIFT is used for feature extraction and matching is performed by unit vectors
