Single-Sample Finger Vein Recognition via Competitive and Progressive Sparse Representation

As an emerging biometric technology, finger vein recognition has attracted much attention in recent years. However, single-sample is a practical and longstanding challenge this field, referring to only one image per class the training set. In recognition, illumination variations under low contrast lack of information intra-class severely affect performance. Despite its high robustness against noise variations, sparse representation rarely been explored for recognition. Therefore, paper, we focus on developing new approach called Progressive Sparse Representation Classification (PSRC) address challenging issue Firstly, as residual may become too large scenario propose progressive strategy refinement SRC. Secondly, adaptively optimize progressions, index Max Energy Residual Index (MERI) defined guidance. Furthermore, extend PSRC bimodal biometrics Competitive (C-PSRC) fusion approach. The C-PSRC creates more discriminative fused sample dictionary by comparing errors different modalities. By with several state-of-the-art methods three benchmarks, superiority proposed clearly demonstrated.