Palm Vein Recognition Based on NPE and KELM

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