摘要
针对红外图像对比度低和细节信息少的特性,提出一种能保持亮度和增强细节的方法。改进的自适应双边滤波将图像分成基本层和细节层,在基本层利用基于高斯混合模型的直方图规定化实现亮度保持,在细节层利用人眼视觉特性自适应选取增强函数来增强较弱细节并保护原图像中的清晰边缘不失真,再恢复到原来灰度空间。研究结果表明:该算法可保持整体明暗视觉效果,同时,原图像中较暗和较亮处的细节都可得到有效增强。
To alleviate the problems of low contrast and less detail of infrared images, a novel algorithm for infrared image enhancement was proposed. An adaptive bilateral filter was employed to extract a base component and a detail component from the original image. Then luminance on the base component was adaptively modified based on Gauss mixture model to persevere brightness. Meanwhile, the detail component was enhanced by a scale adaptive strategy that could emphasize features with low contrast and protect the strong contrast features from distortions. The results show that by the proposed algorithm, the details in both brighter and darker regions of the original images are enhanced and preserved.
出处
《中南大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2016年第6期1967-1972,共6页
Journal of Central South University:Science and Technology
基金
国家自然科学基金资助项目(61372167)~~
关键词
红外图像
双边滤波
高斯混合模型
亮度保持
细节增强
infrared image
bilateral filter
Gauss mixture model
brightness preservation
detail enhancement
