基于激光扫描的残缺指纹图像特征提取技术研究

Research on feature extraction of incomplete fingerprint image based on laser scanning

传统的指纹识别常采用基于纹理边缘轮廓检测方法,不能对残缺指纹进行有效识别,为了实现对残缺指纹图像特征的有效辨认识别,提出一种基于激光扫描的残缺指纹图像特征提取技术。对激光扫描采集残缺指纹图像进行边缘像素集特征分解与角点检测,采用Harris角点检测技术进行残缺指纹非规则角点标记,对激光扫描指纹图像进行边缘轮廓分割,结合指纹的先验纹理特征进行信息融合和残缺点特征提取。仿真结果表明,采用该方法进行残缺指纹图像特征提取,输出图像的峰值信噪比较高,提高了对残缺指纹的有效识别精度。

The traditional fingerprint recognition usually adopts texture edge contour detection method,which cannot effectively identify incomplete fingerprint. Therefore,this paper proposes a feature extraction of incomplete fingerprint image technology based on laser scanning. Feature decompose and corner detect the edge pixels,mark irregular corner of incomplete fingerprint based on Harris corner detection technology,segment edge contour,fuse information and extract incomplete fingerprint combined with transcendental texture feature of fingerprint. The simulation results show that the proposed method can extract the features of incomplete fingerprint image,and the peak signal noise of the output image is relatively high.