系统工程与电子技术

• 软件、算法与仿真 • 上一篇    下一篇

一种光照不均匀图像的自适应校正算法

王殿伟1,2, 王晶3, 许志杰3, 刘颖1,2   

  1. 1. 西安邮电大学通信与信息工程学院, 陕西 西安 710121; 2. 电子信息现场勘查应用技术公安部重点实验室, 陕西 西安 710121; 3. (英国)哈德斯菲尔德大学计算机与工程学院, Huddersfield HD1 3DH, UK
  • 出版日期:2017-05-25 发布日期:2010-01-03

Adaptive correction algorithm for non-uniform illumination images

WANG Dianwei1,2, WANG Jing3, XU Zhijie3, LIU Ying1,2   

  1. 1. School of Telecommunication and Information Engineering, Xi’an University of Posts and Telecommunications,Xi’an 710121, China; 2. Key Laboratory of Electronic Information Application Technology for Scene Investigation, Ministry of Public Security, People’s Republic of China, Xi’an 710121, China; 3. School of Computing and Engineering, University of Huddersfield, Huddersfield HD1 3DH, UK
  • Online:2017-05-25 Published:2010-01-03

摘要:

为了提高光照不均匀条件下采集的图像的视觉效果,提出了一种基于改进二维伽马函数自适应亮度校正算法。首先基于光照反射成像模型,利用快速引导滤波算法提取出光照信息;然后构造了一种改进的二维伽马函数,并利用光照的分布特性动态地调整二维伽马函数的参数,实现对图像亮度的自适应校正处理,提高光照过暗区域图像的亮度值,降低光照过强区域图像的亮度值,得到增强后的图像。对多种场景图像的处理结果表明,本文算法可以有效地降低不均匀光照的影响,提高图像的质量。

Abstract:

An adaptive correction algorithm for non-uniform illumination images is proposed, which can eliminate the impact of non-uniform illumination on imaging results. Firstly, the illumination component is extracted by the fast guided image filter based on the luminance-reflection imaging model. In succession, an improved twodimentional Gamma function dynamically adjusted by the local distribution characteristics of illumination is constructed, which can increase the intensity value at the low-level illumination regions and vice versa at the high-level illumination regions in the luminance domain. Finally, the non-uniform illumination image is adjusted adaptively by the proposed algorithm. Experimental results of different imaging scenarios show that the proposed algorithm can reduce the impact caused by non-uniform illumination and enhance the quality of the images.