基于MMTD的保留灰度值的直方图均衡化  

A Gray Value Retention Histogram Equalization Based on MMTD

作　　者：葛彬[1] 周宁宁[1,2] 

机构地区：[1]南京邮电大学计算机学院,江苏南京210003 [2]软件开发环境国家重点实验室,北京100191

出　　处：《计算机技术与发展》2012年第12期63-66,共4页Computer Technology and Development

基　　金：国家自然科学基金资助项目(61170322);软件开发环境国家重点实验室开放课题(SKLSDE-2011KF-04)

摘　　要：直方图均衡化是图像处理领域中利用图像直方图对对比度进行调整的方法,其"中心思想"是把原始图像的灰度直方图从比较集中的某个灰度区间变成在全部灰度范围内的均匀分布。传统的直方图均衡化图像增强方法存在着灰度级合并的缺点,为了保留更多图像细节,采用一种保留灰度级的直方图均衡化的方法。在该方法中,利用中介真值程度来判断是用保留高灰度级的直方图均衡化还是保留低灰度级的直方图均衡化。用该方法处理的图像要比传统的直方图均衡化算法处理结果效果好。Histogram equalization is the use of image processing to adjust the contrast of the image histogram, the ＂ central idea＂ is to change the original image histogram from the more concentrated gray-scale range of gray scale range into all the uniform distribution. There is a shortcoming that gray-scale merging exists in traditional histogram equalization image enhancement. In order to retain more image detail, use a method retained a gray-level histogram equalization. In this method, use the measure of medium truth scale to deter- mine to use histogram equalization which retains high gray level or histogram equalization which retains the low gray-level. The images that are treated with this method is better than the ones that are treated with traditional histogram equalization.

关 键 词：图像增强 直方图均衡化 中介真值程度 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]