自适应直方图均衡化图像增强算法研究  

Adaptive Image Enhancement Algorithm Based on Histogram Equalization

作　　者：王超[1] 孙玉秋[1] 徐石瑶 余美晨 李祖胜[1] 

机构地区：[1]长江大学信息与数学学院,湖北荆州434023 [2]武汉科技大学信息科学与工程学院,湖北武汉430080

出　　处：《长江大学学报（自然科学版）》2018年第1期55-59,共5页Journal of Yangtze University(Natural Science Edition)

基　　金：国家自然科学基金项目(60572048);湖北省自然科学基金重点项目(2013CFA053)

摘　　要：直方图均衡化图像增强算法原理简单,同时是可逆操作,即只要知道变换函数,就可以通过其逆函数来得到原始的直方图,并且处理的数据量也不是很大,但在增强处理过程中因大量灰度级被合并而导致处理后图像出现不自然的情况。为此,提出了自适应直方图均衡化图像增强算法。该算法根据原始图像的直方图,自适应地确定一个剪切系数,然后按照剪切系数对直方图进行剪切,最后进行均衡化处理。算法的创新点在于自适应确定剪切系数,解决有高峰直方图图像增强后局部不自然的问题。试验结果表明,该算法对直方图有高峰的图像有较好的增强效果并避免过度增强不自然的问题,在计算机图像处理上有较高的应用价值。Aiming at the problem of processing images with the image enhancement algorithm base on histogram equalization,on the basis of its improvement,a novel image enhancement algorithm based on histogram equalization is proposed by using an adaptive method.And the histogram is cut according to the coefficient It carries on the equalization processing.The algorithm does not need to specify the shear coefficient artificially,and it can solve the problem that is unnatural after the image with the peak of the histogram is enhanced.The innovation of this paper is to determine the shear coefficient adaptively,and to solve the problem of local unnatural after the enhancement of the image with the peak of the histogram.The experimental results show that the algorithm has better effect on the imagewith the peak of the histogram and avoids the problem of excessive reinforcement.It has higher application value in computer image processing.

关 键 词：自适应图像增强 直方图均衡化 高峰直方图图像 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]