CAJ | 학술논문

研究并实现了指纹识别过程中用到的算法，实现一套主要包括指纹图像灰度归一化和均衡化、指纹图像分割、二值化的指纹识别预处理算法、不同方向Gabor滤波的特征提取算法；尤其是采用基于Gabor滤波的指纹图像增强和纹理匹配的方法，兼顾了指纹图像的细节特征和全局特征。最后，以matlab7．0为开发平台对该方法进行验证，表明在同样的特征提取算法和匹配的条件下，改进的处理算法能够更简洁而有效地避免各种伪特征且识别率高于传统算法。
연구병실현료지문식별과정중용도적산법，실현일투주요포괄지문도상회도귀일화화균형화、지문도상분할、이치화적지문식별예처리산법、불동방향Gabor려파적특정제취산법；우기시채용기우Gabor려파적지문도상증강화문리필배적방법，겸고료지문도상적세절특정화전국특정。최후，이matlab7．0위개발평태대해방법진행험증，표명재동양적특정제취산법화필배적조건하，개진적처리산법능구경간길이유효지피면각충위특정차식별솔고우전통산법。
A set of fingerprint recognition algorithm is achieved, mainly including Gamma controller normalization and equalizing, fingerprint image division, fingerprint image binarization and different direction Gabor filter for feature extraction; especially fingerprint image enhancement and the textures based on Gabor filter, taking account of both global and local features of the fingerprints. It uses matlab 7.0 as development platform to verify the method. The experimental results show that the proposed algorithm can avoid all sorts of false characters more effectively and recognition rate is higher than traditional algorithm in the same conditions.