Gabor function-based fingerprint enhancement algorithm in wavelet domain
基于Gabor函数的小波域指纹图像增强算法

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.