Palmprint Recognition Based on Line and Slope Orientation Features

Abstract

In the field of palmprint recognition, the orientation information of the principal lines and winkles has long been considered the most dominant and reliable feature. Numerous studies have tried to extract the line orientation information. Among them, the orientation based coding methods such as robust line orientation code (RLOC) and binary orientation co-occurrence vector (BOCV) showed highly promising results. However, the orientation information of pixels that are not located on the palm lines could be greatly affected by the lighting conditions. To solve this problem, this paper proposes a new combined approach using both the line orientation and the slope orientation. When a palm image is hypothetically considered as a 3-D terrain, the principal lines and winkles are deep and shallow valleys on a palm landscape. If the previous line-based approaches focus only on the direction of valleys to investigate the palm landscape, this study focuses on the slope direction of local plains as well as the direction of valleys. The proposed method extracts two different orientation features according to the location of pixels and computes the feature distance between two images by a pixel-to-area matching method. Experimental results show that the proposed approach is superior to several state-of-the-art methods based on the line orientation coding.