保持亮度的多峰值直方图均衡算法  

Brightness Preserving Multipeak Histogram Equalization

作　　者：翟东清[1] 吴陈[1] 曾庆军[1] 

机构地区：[1]江苏科技大学电子信息学院,江苏镇江212003

出　　处：《计算机仿真》2009年第1期222-224,共3页Computer Simulation

基　　金：江苏省科技计划项目(BE2006086)

摘　　要：现有的直方图均衡算法在增强图像对比度的同时,输出图像的亮度与输入图像无关,并且在均衡区域产生亮度饱和现象,提出了一种新的直方图均衡算法。以亮度保持的双直方图均衡算法(BBHE)为基础,改进其对子图像的分类方式:根据直方图对图像进行多峰值分解,得到一系列不同范围的子图像,然后对每一个子图像在其相应的灰度范围内进行直方图均衡,最后合并这些子图像的均衡结果。实验结果表明,直方图均衡新算法不仅在保持了输出图像亮度的同时,而且非常有效的解决了在原图像均衡区域产生的亮度饱和问题对图像的影响。When the traditional algorithm for histogram equalization is used to enhance the contrast of an image, the output brightness is always not related to the input image and causes an effect on brightness saturation in some almost homogeneous area, therefore, the brightness preserving muhipeak histogram equalization is proposed. Based on the algorithm of contrast enhancement using brightness preserving bi - histogram equalization （ BBHE ）, the paper changes the way of classification for sub - image ： based on the histogram, the image is separated into series of sub - images with different gray range, then the histograms are equalized over their corresponding gray range, and finally the output of the image is composed with the resuhing equalized sub - images. The simulation results show that, with the new algorithm, the effect of brightness saturation can be defeated as well as the output image can be preserved..

关 键 词：直方图均衡 亮度保持 多峰值直方图 亮度饱和 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]