中文摘要：

针对掌纹在非接触采集时易出现模糊现象从而导致系统识别性能降低的问题，建立了区域到点的特征映射模型，提出了一种基于区域特征映射（Region featuremap，RFM）的模糊掌纹识别方法．首先根据图像的模糊原理，建立等价的模糊模型，获取模糊掌纹；然后使用RFM对模糊掌纹进行操作，将高维的区域特征映射到低维的点特征：最后，采用归一化相关性分类器对掌纹所属类别进行判定识别．使用模糊模型对PolyU掌纹库进行处理得到PolyU模糊掌纹库，并分别在PolyU掌纹库和PolyU模糊掌纹库上进行测试，识别结果较为稳定．在模糊掌纹库上，本文算法的等错误率（Equal error rate，EER）最小可达0．9069％，优于传统算法，且进行一次识别的时间为33．95ms，得到的特征数据维数较小，降低了算法复杂度，表明了本文算法的有效性和实时性．

英文摘要：

Capuring palmprints with non-contact devices may lead to the blur phenomenon and degrade the performance of recognition system. In order to address this issue, a mapping model from regions to points is established and a novel recognition approach based on region feature map （RFM） is proposed in this paper. According to the theory of blurred image, an equivalence model is firstly established to obtain blurred palmprint image. Then, high-dimensional regional feature is mapped to low-dimsional point feature by using RFM. Finally, normalized correlation classifier is used for determing palmprint category. Furthermore, the blurred PolyU palmprint database is obtained using blur model, and experiment results are stable in the PolyU and blurred PolyU palmprint database using RFM algorithm. The equal error rate （EER） of the proposed method is 0.9069% in the blurred PolyU palmprint database, which is superior to traditional algorithms. Complexity of the algorithm, and recognition time is only 33.95 ms. The effectiveness and real- time performance of our proposed method is verified.