基于自适应多子直方图均衡的图像增强算法

摘要

传统的直方图均衡算法存在一些缺陷,如局部过增强现象和增大图像噪声.针对这些缺陷,提出了自适应多子直方图均衡算法,该算法首先对原始图像的直方图进行分割,接着对子直方图的灰度级进行重新映射,然后重新分割映射后的直方图,调整直方图中灰度级的频率,最后分别对各个子直方图进行均衡处理.实验表明,该算法能够在对图像进行增强的基础上,有效地降低了过增强的影响,同时在保持图像细节方面有比较好的表现.%Conventional histogram equalization has some shortcomings, such as increasing image noise and local excessive enhancement. To overcome such shortcomings, this paper proposes an image enhancement algorithm based on adaptive multi sub-histogram equalization. Firstly, divide the histogram of original image into four sub-histogram;then, remap the gray level of each sub-histogram;next, divide the histogram once again and adjust the frequency of the gray level in the sub-histo-grams; finally, the histogram equalization is implemented to each sub-histogram. Simulation results indicate that the improved algorithm not only can reduce the effect of local excessive enhancement, but also preserve the details of the original image.