针对基于引导滤波的指静脉图像增强算法不能突出静脉纹理细节信息的问题, 提出了基于边缘检测加权引导滤波算法。通过计算指静脉图像的边缘算子幅值, 对引导滤波中固定的规整化因子进行惩罚, 分别得到了静脉纹理区域和平滑区域的自适应规整化因子, 从而使滤波器具有更好的边缘保护特性。该算法在降低噪声的同时, 能保留并突出图像更多的静脉纹理细节。在国内和国外两个数据库上, 对基于边缘检测加权引导滤波与基于引导滤波的两类指静脉图像增强算法进行了对比实验, 结果表明, 前者在时间复杂度不变的情况下具有更低的错误识别率。

To solve the problem that the finger vein image enhancement algorithm based on guided filter fails to highlight the vein texture details, the weighted guided filter algorithm based on edge detection is proposed. Through calculating the amplitude value of the vein image edge operator to punish the fixed neat parameter in the guided filter, the adaptive neat parameters of the vein texture area and the smooth area are obtained respectively, which makes the filter possess a better edge protection feature. This algorithm can reduce the noise, and simultaneously retain and highlight more vein texture details of images. A comparison experiment between two finger vein image enhancement algorithms proposed here and based on the guided filter is conducted in domestic and foreign image databases, and the results indicate that, under the condition of time complexity being constant, the former has a lower false recognition rate.