您的位置:首页  > 论文页面

基于鸡群优化的Tetrolet图像自适应增强方法研究

发表时间:2018-08-31  浏览量:207  下载量:55
全部作者: 胡峰,黄勇,杨勇,代劲
作者单位: 重庆邮电大学计算机科学与技术学院,计算智能重庆市重点实验室
摘 要: 针对现有图像增强方法增强后的图像整体偏暗、细节丢失和失真等问题,提出一种新的基于鸡群优化(chicken colony optimization,CSO)的Tetrolet图像自适应增强方法。采用图像的灰度信息熵为目标函数,将主观图像增强的问题转变为最优化的问题。首先,对图像的灰阶亮度进行多尺度Retinex(multi-scale Retinex,MSR)图像增强;其次,对增强后的图像进行Tetrolet变换,并对高频分量进行非线性调整,再进行Gamma校正;最后,采用CSO算法对目标函数进行优化求解,获得图像增强的最优的非线性函数调整参数和Gamma校正参数,从而实现图像的自适应增强。在3种实验场景下的对比结果表明,本文方法不仅在主观感受上实现了较好的图像增强,同时对客观评价指标——对比度和信息熵有较大的提高。
关 键 词: 计算机应用;图像自适应增强;多尺度Retinex;Tetrolet变换;Gamma校正;鸡群优化
Title: Research on Tetrolet image self-adaption enhancement method based on chicken colony optimization
Author: HU Feng, HUANG Yong, YANG Yong, DAI Jin
Organization: Chongqing Key Laboratory of Computational Intelligence, College of Computer Science and Technology, Chongqing University of Posts and Telecommunications
Abstract: For the problems of existing image enhancement methods in entire dark, detail loss and distortion after image enhancement, a novel Tetrolet image self-adaption enhancement method based on chicken colony optimization (CSO) is proposed. Using the gray information entropy of image as the objective function, the problem of subjective image enhancement is changed into an optimization problem. Firstly, multi-scale Retinex (MSR) image enhancement is taken on grey scale and brightness of image. Secondly, Tetrolet transform is taken afterwards, and the nonlinear adjustment on the high frequency component is done, then Gamma image correction is taken. Finally, the CSO algorithm is used to optimize the solution of objective function in order to achieve optimal nonlinear function parameters and Gamma image correction parameters, then the self-adaption enhancement of image is achieved. Comparison result of experiments on 3 scenarios indicate that this method not only achieve better image enhancement in subjective feeling, but also greatly improve the objective evaluation results of contrast and information entropy.
Key words: computer applications; image self-adaption enhancement; multi-scale Retinex; Tetrolet transform; Gamma correction; chicken colony optimization (CSO)
发表期数: 2018年8月第16期
引用格式: 胡峰,黄勇,杨勇,等. 基于鸡群优化的Tetrolet图像自适应增强方法研究[J]. 中国科技论文在线精品论文,2018,11(16):1607-1617.
 
0 评论数 0
暂无评论
友情链接