基于Gabor滤波的指纹图像增强

Fingerprint Enhancement Based On Gabor Filter

在指纹识别系统中,图像增强效果的好坏对特征提取及指纹鉴别的识别率具有决定性的影响。根据指纹图像具有方向性和频率的特点,把Gabor滤波器应用在指纹图像增强处理中。利用Gabor滤波器的方向选择和频率选择特性,把指纹图像的局部方向和脊线频率作为Gabor滤波函数的参数,然后把Gabor函数与纹理图像进行卷积,从而去除了噪声,达到了增强图像的目的。在算法设计上提高了运算速度,节省了运算的时耗。实验证明,算法工作稳定,效果好,具有很强鲁棒性。

In fingerprint recognition system, the results of image enhancement have an important affect on Minutia extracting and recognition. A Gabor filter is applied in the fingerprint image enhancement according to its characteristic which is a kind of special image that has characters of direction and frequency. Also, a Gabor filter has characters of direction and frequency selectivity. Accordingly, we can use the local direction and frequency of the fingerprint image as the Gabor filter function＇s parameters, and then compute the convolution of the Gabor filter and fingerprint images. In this way, we remove noises from fingerprint images effectively and enhance fingerprint images. In this paper, an algorithm which enhances the calculation speed and reduce the operation time is designed. From the experimental results, we prove that this algorithm is steady, effective and robust.