基于CLAHE和多尺度细节融合的静脉图像增强算法

Vein Image Enhancement Based on CLAHE and Multi-scale Detail Fusion

摘要:

利用静脉识别原理采集的静脉图像通常模糊不清、难以分辨。传统的CLAHE算法虽然能够提高静脉图像的对比度,但是会丢失图像的一些细节信息。文章提出了一种基于CLAHE和多尺度细节融合的静脉图像增强算法。首先对静脉图像进行ROI提取,采用CLAHE算法增强静脉与手背间的对比度；然后利用多尺度细节融合算法得到静脉图像的细节图,再通过均值滤波滤除细节层中的高频噪声；最后把上面两种方法得到的图像加权叠加得到细节增强后的静脉图像。实验结果表明,该方法在提高静脉图像对比度的同时保留了原图像的细节信息。

Abstract:

The vein images collected by using the principle of vein recognition are usually blurred and difficult to distinguish. The traditional CLAHE algorithm can improve the contrast of vein images, but will lose some details of the image. Therefore, a vein enhancement algorithm based on CLAHE and multi-scale detail fusion is proposed. Firstly, the ROI of the vein image is extracted, and the CLAHE algorithm is used to enhance the contrast between the vein and the back of the hand. Then, the multi-scale detail fusion algorithm is used to obtain the detailed image of the vein image, and then the high-frequency noise is filtered out in the detail layer through the average filter. Finally, the images obtained by the two methods are weighted and superimposed to obtain vein images with enhanced details. Experimental results show that this method not only improves the contrast of the vein images, but also retains the details of the original images.