基于细节拉伸和亮度调节的图像增强方法分析  

Analysis of Image Enhancement Method Based on Detail Stretching and Brightness Adjustment

作　　者：陆振林 任永正 李欣 荣金叶 LU Zhenlin;REN Yongzheng;LI Xin;RONG Jinye(Beijing Institute of Microelectronics Technology,Beijing 100076,China)

机构地区：[1]北京微电子技术研究所,北京100076

出　　处：《电子技术（上海）》2024年第6期52-55,共4页Electronic Technology

摘　　要：阐述在视频图像监控领域,由于光照不均匀,图像往往有低照度区域、过亮区域,无法观察到大量细节的区域,为此,提出一种局部细节增强和全局亮度调节的方法。首先使用引导过滤器将输入图像分为基础层和细节图层。过滤完成后,用arctan函数拉伸细节层,用基础层的亮度分量来调整细节层,并与基础层线性组合以增强细节。最后利用最大熵引导的自适应曲线调整图像、亮度,提高低光和过亮区域的对比度。实验证明,该方法可以显著提升非均匀照度图像的质量,并且具有运行耗时低的优势。This paper describes that in the field of video image surveillance,due to uneven illumination,the images often have areas with low illumination areas,over-lit areas,where a large number of details cannot be observed.Improving the contrast of these areas and improving the visibility of the images is an important issue.It presents a method for local detail enhancement and global brightness regulation.The input image was first divided into the base layer and detail layer using Guide Filter(GF).After the filtering is completed,the detail layer is first stretched with the arctan function,and then the brightness component of the base layer is used to adjust the detail layer,and then linearly combined with the base layer to enhance the detail.Finally,the image was adjusted using the maximum entropy-guided adaptive curve to adjust the brightness and improve the contrast of low and over-lit regions.Experimental results show that our proposed algorithm has significant results in enhancing uneven illumination images and has the advantage of low running time consuming over some popular algorithms.

关 键 词：视频图像 细节增强 亮度调节 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]