Palm Vein Recognition Based on NPE and KELM

Abstract

Palm veins have become a research hotspot of biometric recognition due to their own advantages of universality, uniqueness, collectability and stability. This paper proposes a palm vein recognition algorithm based on Neighborhood Preserving Embedding (NPE) and Kernel Extreme Learning Machine (KELM). The algorithm firstly performs gray-scale normalization processing on vein images, then extracts neighborhood preserving embedding dimensionality reduction features, and finally uses extreme learning machine for classification and recognition. The method is tested on the multispectral palmprint database of Hong Kong Polytechnic University. The experimental results show that this method can effectively reduce the vein dimensions to less than 30, and achieve an ideal recognition effect, if the parameters are selected appropriately. The algorithm is also verified on the palmvein database of Tongji University and FYO palmvein database for verifying the robustness, and also get ideal experimental results.