基于人手自然张开的多生物特征识别

Multi-biological features recognition based on natural open of hand

手形和掌纹作为人手重要的生物特征可以用来进行身份识别。在人手自然张开、非接触式的采集条件下,基于手形识别匹配速度快和掌纹识别的识别率高的优点,采用基于匹配层的手形和掌纹融合方法,克服了单一手形识别的识别率低和掌纹识别匹配速度慢的缺点。手形采用手指的相对长度作为特征矢量,掌纹采用2D-Gabor对掌纹感兴趣区域(ROI)进行滤波,提取掌纹纹线的方向信息作为特征。在混合图库上进行实验,二者相结合的组合识别方法的识别率达到98.57%,减少了匹配时间。同时也研究了对于不同距离采集的手掌图像,实验结果表明手形和掌纹相结合的组合识别方法优势更为明显。

Hand-shape and palm-print as biological characteristics can be used for identification.In this paper,the method of combining the hand-shape and palm-print in the matching layer was adopted according to the merit of the high speed of palm-print identification and high matching rate of hand-shape.This method successfully conquered the weakness of the low recognition rate of hand-shape and the low matching speed of palm-print identification.The hand fingers relative length in hand-shape could be used as feature vector,and the 2-D Gabor in palm-print was used to extract the direction of palm-print lines as the feature information from the region of interest（ROI） of palm-print.The recognition rate of combining with them can achieve 98.57%,and the matching time was reduced.In addition,the collected palm image in different distance was also researched in this paper.The experimental results show that the advantages of combination of the palm-print and hand-shape image is more obvious.