Palmprint Linear Feature Extraction and Identification Based on Ridgelet Transforms and Rough Sets

As one of the most important biometrics features, palmprint with many strong points has significant influence on research. In this paper, we propose a novel method of palmprint feature extraction and identification using ridgelet transforms and rough sets. Firstly, the palmprints are first converted into the time-frequency domain image by ridgelet transforms without any further preprocessing such as image enhancement and texture thinning, and then feature extraction vector is conducted. Different features are used to lead a detection table. Then rough set is applied to remove the redundancy of the detection table. By this way, the length of conduction attribute is much shorter than that by traditional algorithm. Finally, the effectiveness of the proposed method is evaluated by the classification accuracy of SVM classifier. The experimental results show that the method has higher recognition rate and faster processing speed.