基于自适应遗传算法的红外子热像图模糊增强方法  

Fuzzy enhancement of infrared sub thermal image based on adaptive genetic algorithm

作　　者：马瑞[1] MA Rui(School of Information and Intelligent Engineering,Anhui Vocational College of Electronics and Information Technology,Bengbu 233030,China)

机构地区：[1]安徽电子信息职业技术学院信息工程学院,安徽蚌埠233030

出　　处：《湖南文理学院学报（自然科学版）》2024年第3期30-36,共7页Journal of Hunan University of Arts and Science(Science and Technology)

基　　金：安徽省教育厅安徽高校科学研究重点项目(KJ2021A1488);安徽电子信息职业技术学院自然科学项目(2022AHDZZK03)。

摘　　要：为了提高红外子热像图的边缘强度、信息熵和清晰度等,使图像视觉效果有所提高,研究了一种基于自适应遗传算法的红外子热像图模糊增强方法。对含有噪声的红外子热像图展开小波变换,分别获取高、低频小波系数,低频部分的小波系数不进行任何处理,高频部分的小波系数引入最小二乘对其进行总体估计,同时逆变换处理估计后的小波系数,完成红外子热像图去噪处理。通过模糊增强算法增强处理红外子热像图,同时引入自适应遗传算法优化处理模糊参数,实现红外子热像图模糊增强。实验结果表明,本文所提方法的图像更加清晰,且对比度也明显得到改善,其平均对比度值为0.075,平均边缘强度值为67.14,平均信息熵值为8.59,平均清晰度值为13.73,充分说明该方法获取的红外子热像图模糊增强效果更加理想,能够有效提升视觉效果。In order to improve the edge intensity,information entropy and sharpness of infrared sub thermal image,a fuzzy enhancement method of infrared sub thermal image based on adaptive genetic algorithm is studied.The wavelet transform of infrared sub thermal image with noise is carried out to obtain the wavelet coefficients of high and low frequency respectively.The wavelet coefficients of low-frequency part are not processed at all,while the wavelet coefficients of the high-frequency part are estimated by the least square method,and the estimated wavelet coefficients are processed by the inverse transform to denoise the infrared sub thermal image.The infrared sub thermal image is enhanced by fuzzy enhancement algorithm,and the fuzzy parameters are optimized by adaptive genetic algorithm.The experimental results show that the image of the proposed method is clearer and the contrast is obviously improved.The average contrast value is 0.075,the average edge intensity value is 67.14,the average information entropy value is 8.59,and the average definition value is 13.73,which fully shows that the fuzzy enhancement effect of the infrared sub thermal image obtained by this method is more ideal and can effectively improve the visual effect.

关 键 词：自适应遗传算法 红外子热像图 模糊增强 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]