一种基于模板匹配的手指静脉识别算法

相对于指纹识别等传统生物特征识别手段，手指静脉识别是一种新兴的具有较好应用前景的生物特征识别技术。本文设计了具有自适应光源系统的手指静脉采集仪，能够自动获得亮度均匀的手指静脉图像；提出了一种基于模板匹配的手指静脉识别算法，采用基于多方向灰度谷底搜寻方法提取手指静脉特征，然后将从同一手指多个图像中提取的静脉特征合成模板，并通过门限阈值消除模板中的随机差异信息。实验结果表明，运用本研究提出的基于模板匹配的手指静脉识别算法能有效提高识别准确性，具有99.10%的识别准确率和1.03%的等错误率。

A finger vein recognition algorithm based on template matching

Compared with fingerprint recognition and other traditional biometric recognition method,finger vein rec?ognition is a new biometric technology that has a good application prospect. To improve imaging quality of finger vein identification system,a light system that can automatically adjust the luminous intensity was designed. Finger vein feature extraction process was conducted based on a multi-directional gray scale valley point search method. In the finger vein template synthesis process,a threshold was used to eliminate the random variation information in the tem?plate. Results show that using template with less random variation information can help improve recognition accura?cy. The proposed finger vein recognition algorithm has an accuracy rate of 99.10%and an equal error rate of 1.03%.