尺度优化的Retinex增强算法与微视觉图像增强  

Retinex Enhancement Algorithm with Scale Optimization and Micro Vision Image Enhancement

作　　者：余金栋[1] 张宪民[1] 陈忠[1] 

机构地区：[1]华南理工大学广东省精密装备与制造技术重点实验室,广东广州510640

出　　处：《华南理工大学学报（自然科学版）》2013年第2期7-11,共5页Journal of South China University of Technology(Natural Science Edition)

基　　金：国家自然科学基金重大研究计划项目(91223201);NSFC-广东省自然科学联合基金资助项目(U0934004);华南理工大学中央高校基本科研业务费专项资金资助项目(2012ZP0004)

摘　　要：光照不均匀、光学显微镜的放大作用、光学衍射等使微视觉图像存在动态范围大、整体像素灰度值偏低、微细结构与背景对比度低、信噪比低等不足.为增强图像质量,文中利用对比度设计高斯平滑卷积核的尺度优化准则以合理估计光照分量,提出了尺度优化的Retinex增强算法,并用该算法对模拟图像和实拍的同轴光光强变化的微视觉图像进行增强.结果表明,该增强算法在压缩动态范围内既能提高对比度,又能较好地保留图像细节信息,增强效果优于同态滤波算法.Due to the existence of non-unifiorm illumination, magnification effect of optical microscope and optical diffraction, etc. , micro-vision images are of large dynamic range, low overall pixel gray value, low contrast of fine structure to background and low signal-to-noise ratio. In order to improve the image quality, a Retinex enhaneemenf algorithm with scale optimization is proposed. This algorithm uses the contrast to design an optimization criterion of Gauss smoother convolution kernel scale for the reasonable estimation of illumination component. The algorithm is then applied to the enhancement of simulated images and micro-vision images generated under various coaxial light intensities. The results show that the proposed algorithm is superior to the homomorphic fihering one because it improves the contrast and reserves the image details within the dynamic compressing range.

关 键 词：显微图像 图像增强 RETINEX算法 光照不均匀 尺度优化 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]