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.
出处
《红外技术》
CSCD
北大核心
2010年第10期601-603,607,共4页
Infrared Technology
关键词
红外图像增强
MSR
梯度权值
直方图均衡
infrared image enhance
multi-scale Retinex（MSR） algorithm
gradient weight
histogram equalization
