Gabor函数实现基于结构的指纹识别

为了解决传统的基于细节点的指纹识别算法的不足,提出了基于结构的指纹识别算法.该算法根据指纹纹线间距均匀且局部平行的特点,建立了用于指纹识别的Gabor滤波函数的物理模型,设计了Gabor滤波函数的优化参数和格栅方案,有效地提取了指纹的全局和局部特征.该算法提高了有限面积内的指纹信息利用率,具有增强指纹图像的脊线并抑制噪声的作用.通过在标准指纹数据库上用不同参数和方案的对比实验,验证了该理论分析的正确性.

Structure-based fingerprint recognition using Gabor filters

A structure-based fingerprint recognition algorithm was proposed in order to overcome the drawback of the traditional minutiae-based fingerprint recognition algorithm. According to the local parallel of ridges and furrows of fingerprint images, the physical model of Gabor filtering function was established, and the parameters and the grid of Gabor function were optimized theoretically and experimentally. The proposed method captures both the whole and local features of fingerprint images effectively. The algorithm improves the utilization ratio of the information contained in the fingerprint images, and enhances the ridge and restrains the noise. The result of the comparison experiment and comparison with other traditional method show the efficiency of the Gabor filters and the recognition method.