A contour extraction algorithm of palmprints based on corner point features

Abstract

An algorithm to extract contour of palmprint based on corner point features is proposed. Firstly, a lot of excircles were made along the edges of palmprint; Secondly the approximate corner point positions of palmprint can be located by calculating the intersection number of palmprint edges and the excircles; Finally, extract ROI region by the means of inscribed circle of square, then extract and match the texture feature by combining with palmprint features and relative knowledge. On the basis of corner positions, a consistent ROI can be extracted for each palmprint, and feature vectors can be calculated for each ROI to match all the palmprint images in the database. The experimental results show that the palmprint is a good biological feature for identity authentication recognition, and the corner point detection algorithm not only can position the corner point quickly and accurately, but also can improve the matching efficiency effectively.