Palmprint Classification Using Multiple Advanced Correlation Filters and Palm-Specific Segmentation
There is increasing interest in the development of reliable, rapid and non-intrusive security control systems. Among the many approaches, biometrics such as palmprints provide highly effective automatic mechanisms for use in personal identification. This paper presents a new method for extracting features from palmprints using the Competitive Coding Scheme and angular matching. The Competitive Coding Scheme uses multiple 2-D Gabor filters to extract orientation information from palm lines. This information is then stored in a feature vector called the Competitive Code. The angular matching with an effective implementation is then defined for comparing the proposed codes, which can make over 9,000 comparisons within 1s. In our testing database of 7,752 palmprint samples from 386 palms, we can achieve a high genuine acceptance rate of 98.4% and a low false acceptance rate of 3 10%. The execution time for the whole process of verification, including preprocessing, feature extraction and final matching, is 1s.