摘要
色彩恢复多尺度Retinex算法(MSRCR)是在单尺度Retinex算法(SSR)和多尺度Retinex算法(MSR)的基础上进行的改进和增强,其能明显改进上述2种算法的图像偏色效果并扩大图像的动态范围,使图像的明、暗区域细节都能得到很好的体现。给出一种改进的基于MSRCR理论的算法实现,实验表明,该算法实用性强,在图像对比度和细节增强方面都有很好的效果。
Algorithms based on Multi-Scale Retinex with Color Restoration can improve the effect of algorithms of SingleScale Retinex and Multi-Scale Retinex,which can significantly improve the effect of color deviation and expand the dynamic range of images,realize that the details of bright and dark areas of images can be well represented. In this paper,an improved algorithm based on MSRCR theory is presented. And the experimental results show that the algorithm is practical and has a good effect on image contrast and detail enhancement.
引文
[1]李福文,金伟其,陈伟力,等.基于Retinex模型的彩色图像全局增强算法[J].北京理工大学学报,2010,30(8):947-951.
[2]李冠章,罗武胜,李沛.可避免彩色失真的图像对比度增强[J].计算机仿真,2008,25(10):228-231.
[3]杨万挺,汪荣贵,方帅,等.滤波器可变的Retinex雾天图像增强算法[J].计算机辅助设计与图形学学报,2010,22(6):965-971.
[4]洪平.基于Retinex理论的图像去雾研究[D].上海:上海交通大学,2013.
[5]龚薇,斯科,叶秀清,等.一种强鲁棒性的实时图像增强算法[J].传感技术学报,2007,20(9):2024-2028.
[6]李冠章,罗武胜,李沛.适应彩色空间的图像对比度增强算法[J].传感技术学报,2009,22(6):833-837.