Robust Palm-print Recognition Using Multi-resolution Texture Patterns with Artificial Neural Network

Abstract

Palm-print recognition system is extensively deployed in a variety of applications, ranging from forensic to mobile phones. This paper proposes a new feature extraction technique for robust palm-print based recognition. The method combines the angle information of an edge operator and multi-scale uniform patterns, which extracts texture patterns at different angular space and spatial resolution. Thus, making the extracted uniform patterns less sensitive to the pixel level values. Further, an optimal artificial neural network structure is developed for classification, which helps in maintaining the higher classification accuracy by significantly reducing the computational complexity. The proposed method is tested on standard PolyU, IIT-Delhi and CASIA palm-print databases. The method yields an equal error rate of 0.2% and classification accuracy of 98.52% on PolyU database