期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
期号：NCFCSPS
页码：176
出版社：S&S Publications
摘要：This paper develops the accurate personal identification by combining the left and right palmprintimages. The multibiometrics has received much attention in the palmprint identification. We, firstly propose anew approach for image level combination of RGB color to generate more reliable palmprint representation thanthe conventional gray level representation. This investigation is motivated to develop the similarity between theleft and right palmprint images. Secondly this paper analysis the feature representation (SIFT and OLOF) anddifferent database (Poly U and IITD). Then the left and right images to perform matching score-level fusion.The experimental results from this study suggests that the Scale Invariant Feature Transform (SIFT) andOrthogonal Line Ordinal Features, perform significantly better for the contactless palmprint images than otherapproach employed earlier on the more conventional palmprint imaging. The achieved error rates show a goodperformance of these features.
关键词：Multibiometric; Left and Right Palmprint images; SIFT and OLOF; Matlab basics
