联合CLAHE和BM3D的低温红外图像增强算法  

Low temperature infrared image enhancement algorithm combined with CLAHE and BM3D

作　　者：赵楷[1] 李道豫 张琳琳 石飞[1] ZHAO Kai;LI Dao-yu;ZHANG Lin-lin;SHI Fei(College of Information Science and Engineering,Xinjiang University,Urumqi 830046,China;College of Software,Xinjiang University,Urumqi 830046,China)

机构地区：[1]新疆大学信息科学与工程学院,新疆乌鲁木齐830046 [2]新疆大学软件学院,新疆乌鲁木齐830046

出　　处：《计算机工程与设计》2025年第2期329-336,共8页Computer Engineering and Design

基　　金：国家自然科学基金项目(62366052);新疆维吾尔自治区自然科学基金项目(2022D01C429、2022D01C427、2020D01C028)。

摘　　要：针对低温红外图像在温差较小的环境下对比度较低的问题,提出一种基于对比度受限的自适应直方图改进算法,用于低温红外图像去噪和增强。使用双边滤波算法将原始红外图像分解为细节层和基础层;使用CLAHE算法对基础层进行对比度增强,采用BM3D算法对细节层进行去噪,应用拉普拉斯锐化技术增强红外图像的边缘细节;分别赋予基础层和细节层图像不同的权值系数并线性叠加,获得增强后的红外图像。实验结果表明,该算法在视觉效果和客观数据两方面均优于常见的红外图像增强算法。A contrast-limited adaptive histogram equalization(CLAHE)based improvement algorithm for enhancing low-tempe-rature infrared images was proposed to address the low contrast problem of infrared images captured in environments with small temperature differences.The infrared image was hierarchically processed using a bilateral filtering algorithm to decompose original infrared image into base and detail layers.The CLAHE algorithm was used to enhance the contrast of the base layer,the BM3D algorithm was used to denoise the detail layer,and the Laplacian sharpening technique was applied to enhance the edge details of the infrared image.The processed base and detail layers were linearly combined to obtain the enhanced infrared image.Experimental results show that this algorithm is superior to common image enhancement algorithms in terms of visual effects and objective data.

关 键 词：图像增强 低温红外图像 对比度增强 图像去噪 边缘增强 直方图均衡化 双边滤波 

分 类 号：TP317[自动化与计算机技术—计算机软件与理论]