摘要
将粒子群优化算法引入到图像对比度增强中,结合遗传算法全局搜索的优点,提出一种基于混合进化算法的图像模糊对比度增强方法。该算法首先将雾天图像由RGB空间转换到HSV空间,利用高斯隶属度函数模糊化图像,通过隶属度函数与渡越点距离算子定义图像的模糊对比度、模糊熵以及视觉因子,得到待优化目标函数,再通过混合进化算法选择参数,实现图像对比度变换的自适应性。采用图像质量评价函数证明了该算法的有效性。
This paper proposed a fog removal method based on fuzzy contrast optimization using hybrid evolutionary algorithm（FCOHE-FR）, in which, combining with the advantages of genetic algorithm, the particle swarm optimization algorithm is introduced to the image contrast enhancement. By combining the particle swarm optimization algorithm with the genetic algorithm with hybrid evolutionary, a defogging algorithm is presented. Convert fog video from RGB space to HSV space; blur the images by using Gaussian membership function. Define image contrast, fuzzy entropy and visual factor by fuzzy membership function and crossover point distance operator to get the objective function to be optimized. Then, the hybrid evolutionary algorithm is adopted to select parameters to achieve image contrast self-adaptive transform. The effectiveness of the proposed algorithm is proved by the image quality evaluation function.
出处
《计算机时代》
2016年第1期12-18,共7页
Computer Era
基金
浙江省自然科学基金(LQ14F030014
LQ13F030012)
浙江农林大学人才启动基金(2013FR023
2013FR085)
浙江农林大学智慧农林业研究中心预研项目(2013ZHNL03)
浙江省林业智能监测与信息技术研究重点实验室开放基金
关键词
图像去雾
粒子群优化算法
遗传算法
混合进化算法
模糊对比度增强
image defogging
particle swarm optimization algorithm
genetic algorithm
hybrid evolutionary algorithm
fuzzy contrast enhancement
