一种新的仿生彩色图像增强方法  

A Novel Bio-inspired Algorithm for Color Image Enhancement

作　　者：王守觉[1,2] 丁兴号[1] 廖英豪[1] 郭东辉[1] 

机构地区：[1]厦门大学信息科学与技术学院,福建厦门361005 [2]中国科学院半导体研究所,北京100083

出　　处：《电子学报》2008年第10期1970-1973,共4页Acta Electronica Sinica

基　　金：国家自然科学基金主任基金(No.60753001);福建省自然科学基金(No.2008J0032);厦门大学985二期信息创新平台(No.0000-X07204)

摘　　要：基于人类视觉系统的全局和局部自适应特性,本文提出一种仿生彩色图像增强方法,用于增强不均匀光照或低照度情况下的图像.该方法主要包括全局自适应亮度调节、局部对比度增强和颜色恢复三个部分.即全局亮度调节主要用来增强暗区域的亮度和压缩图像的动态范围;局部对比度增强利用当前点与其邻域象素的双边滤波输出之间的关系,调节当前点的亮度,以增强图像局部对比度;再通过一种简单的线性颜色恢复算法恢复图像色彩.与文献[7,8]所提彩色图像增强算法相比,实验结果表明本文所提方法的效果更好.We propose a novel bio-inspired algorithm to enhance the color image under low or non-uniform lighting conditions that models global and local adaptation of the human visual system. The proposed method consists of three parts： a preliminary global luminance adjustment followed by local contrast enhancement and color restoration. The global luminance adjustment increases the luminance of darker pixels and compresses the dynamic range as well. The local contrast enhancement adjusts the intensity of each pixel based on its relative magnitude with respect to the bilateral filter output of its neighboring pixels. Then a linear color restoration process is applied to convert the enhanced intensity image back to a color image. Experimental results of the proposed method and reference [7,8] are compared and analyzed to illustrate the effectiveness of the proposed method.

关 键 词：彩色图像增强 人类视觉系统 RETINEX 双边滤波器 

分 类 号：TN911.73[电子电信—通信与信息系统]