基于MSR结合权值直方图的红外图像增强算法  

Infrared Image Enhancement Algorithm Based on MSR Theory and Weight Histogram Method

作　　者：贺明[1] 王新赛[1] 吴强[1] 郭东[1] 龙云富[1] 

机构地区：[1]防空兵指挥学院红外与成像制导技术实验室,河南郑州450052

出　　处：《红外技术》2010年第10期601-603,607,共4页Infrared Technology

摘　　要：针对红外图像对比度低、细节较差的特点,提出了一种基于MSR结合权值直方图的红外图像增强算法。首先利用多尺度Retinex(MSR)算法,滤除低频噪声,然后再通过数学形态学方法得到图像梯度信息,结合灰度值计算出灰度统计权值,最后将此权值应用于图像直方图均衡算法中,得到增强后图像。实验表明:该算法能够有效增强整体图像,同时较大地提升了图像细节,并且易于工程实践。For the infrared image contrast is low,the details of the features of poor.Proposed a Infrared image enhancement algorithm Based on MSR Theory and Weight Histogram Method in this paper,Firstly,Implement multi-scale Retinex（MSR） algorithm for filtering low frequency noise,Meanwhile,the gradient information of the image is obtained with morphological approach.Together with the original grey value,a weight value for grey-scale statistic is figured out.Finally,the histogram equalization algorithm based on the weight value is adopted to get high-quality image.Experimental results demonstrate that the method can enhance the overall image and the image details effectively,Moreover,this method runs very fast and thus it is promising for practical applications.

关 键 词：红外图像增强 MSR 梯度权值 直方图均衡 

分 类 号：TN911.73[电子电信—通信与信息系统]