基于Gabor函数的小波域指纹图像增强算法

Gabor function-based fingerprint enhancement algorithm in wavelet domain

针对指纹大规模采集库中存在的指纹图像局部区过干或过湿的问题,提出了一种基于Gabor函数的小波域指纹增强算法。该算法在小波域利用低频系数图估计指纹方向,从而抑制了指纹局部过干或过湿的影响,进而分别实现基于Gabor函数的小波域各子图增强,最终将各增强子图利用小波逆变换实现重构。通过对FVC2004的DB1指纹库中的部分低质量图像的增强结果比较,该算法对低质量指纹图像的增强效果明显,且处理速度明显快于现存的Gabor增强方法。

In large-scale fingerprint image databases, there unavoidably exist some over/under inking images. A Gaborbased fingerprint image enhanced algorithm in wavelet domain was proposed based on the idea that the dry and wet can he looked as high-frequency disturbance. After normalized preprocessing and wavelet decomposition, only approximation coefficient image was used to determine the ridge orientation, so that the effect of the dry and wet could be restrained. Then using above estimated ridge orientation, each direction coefficient images were enhanced based on Gabor function and further reconstruction. The simulation results on some typical images in FVC2004 DB1 database show that our proposed algorithm has better enhanced performance and lower computation burden than current Garbor enhancement algorithm.