摘要
提出了一种基于马尔可夫随机场的指纹图像增强新方法 ,它用来描述纹线的局部随机特性 ,然后多次进行曲纹线方向和幅值引导的曲线累积 ,直到能够区分指纹中脊与谷的统计差别 .实验结果表明这种方法不仅能提高指纹图像中纹线脊与谷的对比度 ,还能有效保持纹线的细节特征 .
The fingerprint enhancement scheme based on Markov Random Field(,MRF), which is applied to capture local statistical regularities of ridges, is presented. Then the curve accumulation guided by ridge direction and magnitude is repeated until statistics difference can be acquired between fingerprint ridges and valleys. Experimental results show that this approach can improve the clarity of ridge and valley structures of fingerprint images and meanwhile preserve the minutiae well.
出处
《红外与毫米波学报》
SCIE
EI
CAS
CSCD
北大核心
2003年第4期286-290,共5页
Journal of Infrared and Millimeter Waves
