基于分片光滑照度估计的Retinex图像处理框架  

A Retinex Image Processing Framework Based on Estimation of Piecewise Smooth Illumination

作　　者：吴壮志[1] 齐立娜[1] 骆沛[1] 

机构地区：[1]北京航空航天大学计算机学院,北京100191

出　　处：《国防科技大学学报》2011年第3期83-88,共6页Journal of National University of Defense Technology

基　　金：国家科技支撑计划资助项目(2008BAH29B02)

摘　　要：Retinex理论是一种图像增强技术,其基本原理是将原图像分解为照度图像和反射图像的乘积。传统的Retinex理论假定照度图像是平滑的,在实际场景中,由于目标的反射特征不同及阴影等的影响,照度图像实际上是分片平滑的,导致反射图像边界附近模糊,产生光晕现象。针对上述问题,提出了一种改进的Retinex理论图像处理框架:采用分片平滑算子估算照度图像,消除了光晕现象;引入照度校正功能,调节图像的对比度;引入反射校正功能,进行细节增强和去噪。结合图像质量评价指标,对改进后框架的有效性和正确性进行了分析验证,实验结果表明改进后的方法效果良好。Retinex theory is a kind of technology for image enhancenaent, and its basic principle is to decompose the original image into the product of illumination and reflectance. Traditional Retinex theory generally assumes that illumination is smooth, while in actual scenes, because of effects of different reflection characteristics of targets and shadings, illumination is piecewise smooth, resulting in an edge blurred reflection image and generating halos. For the above problems, this paper proposes an improved image processing framework for Refinex theory. First, the illumination is estimated with piecewise smooth operator to eliminate the halo phenomenon. Second, illumination correction is introduced for adjusting the contrast of the image. Third, reflection correction is introduced for detail enhancement or denoising. In the end, this paper verifies the improved framework with image quality evaluating indicators for the validity and correctness. The experimental results show that the improved framework is effective.

关 键 词：RETINEX 双边滤波 GAMMA校正 图像质量评价 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]