基于Gabor滤波器的自适应指纹增强算法

Adaptive fingerprint image enhancement algorithm based on Gabor filter

指纹增强的目的在于改善指纹图像的质量,进而提高指纹识别系统的性能。提出了一种基于Gabor滤波器的指纹增强算法,算法采用梯度法计算纹线方向,利用指纹图像子块的频谱分布特征计算纹线频率,通过计算图像方向一致性来自适应地调节Gabor滤波窗口的大小,再采用具有可变角度带宽的低通滤波器进行滤波,有效地提高指纹的纹理清晰度,较好地避免奇异点区域的块效应。实验结果表明,算法具有良好的图像增强效果。

Fingerprint enhancement aims to improve the quality of fingerprint images and the performance of fingerprint recog- nition system. A fingerprint enhancement algorithm based on Gabor fiher was proposed in this paper, which used the gradient meth- od to calculate ridge orientation and the frequency spectrum characteristic of fingerprint image sub-block to calculate ridge frequen- cy. The algorithm adjusted Gabor filter window size adaptively by calculating the image orientation, and implemented the filtering by using a low-pass filter with changeable angle bandwidth, which could effectively improve the clarity of the fingerprint texture and well avoid blocking effect in singular point area. The experimental results indicated that the proposed algorithm is very effective for image enhancement.