基于量子行为粒子群优化的低照度图像增强研究  

Study on low Illumination image enhancement based on quantum behaved particle swarm optimization

作　　者：薛媛媛 张兴忠[2] 赵健彬[3] XUE Yuanyuan;ZHANG Xingzhong;ZHAO Jianbin(Department of Information Engineering,Shanxi Traffic Vocational and Technical College,Taiyuan 030031,China;Software College,Taiyuan University of Technology,Taiyuan 030024,China;College of Architecture and Civil Engineering,Taiyuan University of Technology,Taiyuan 030024,China)

机构地区：[1]山西交通职业技术学院信息工程系,山西太原030031 [2]太原理工大学软件学院,山西太原030024 [3]太原理工大学建筑与土木工程学院,山西太原030024

出　　处：《光学技术》2021年第4期500-506,共7页Optical Technique

基　　金：山西省教育科学“十三五”规划2019年度规划课题(GH-19269)。

摘　　要：针对许多应用领域内所存在的低照度图像,提出了一种基于量子行为粒子群优化的低照度图像增强方法。该方法提取低照度图像的非纹理区域,在图像增强过程中限制非纹理区域的灰度范围,从而抑制伪影现象。在直方图均衡化处理中设计了分级概率密度函数,并运用改进的量子行为粒子群优化算法对分级概率密度函数的参数进行优化。最终在典型的低照度图像上完成了验证实验,结果表明该方法不仅提高了图像的对比度,同时也增强了图像的细节信息与视觉质量。In view of low illumination images existing in many application fields, a low illumination image enhancement method based on quantum behaved particle swarm optimization is proposed. The method extracts non-textural regions of low illumination images, and limits the gray level range of non-textural regions to reduce the artifact situation while enhancing the images. A hierarchical probability density function for Histogram Equalization is designed, the improved quantum behaved particle swarm optimization algorithm is applied to search the optimal parameters of hierarchical probability density function. Finally, validation experiments are carried on typical low illumination images, the results indicate that the proposed method not only improves the contrast of images, but also enhances the detail information and visual quality of images.

关 键 词：低照度图像 量子行为粒子群优化 图像增强 分级概率密度函数 多目标优化问题 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TH691.9[自动化与计算机技术—计算机科学与技术]