This paper suggests a new algorithm to solve problems of the current retinex algorithm such as distortion of grey out and color noise due to the individual treatment of RGB channel and log function,and halo effect occ...This paper suggests a new algorithm to solve problems of the current retinex algorithm such as distortion of grey out and color noise due to the individual treatment of RGB channel and log function,and halo effect occurred by use of the Gaussian filter.The current retinex algorithm treats each channel in RGB space that brings a phenomenon to change the rate of RGB.To improve this phenomenon,the color information was fixed in the HSV color space,and retinex treatment was conducted against the V value,a luminance feature.Linear treatment was carried out to remove color noise occurred by the use of log function.S value,a saturation value was compensated in proportion to the change of V value in luminance to obtain a clearer image.The proposed algorithm was evaluated against the landscape images that had strong backlit phenomena,and it is proved to have a better performance than the current retinex algorithm,multiscale retinex with cdor restoration(MSRCR).展开更多
基金The Brain Korea21Project in 2011 andthe MKE(the Ministry of Knowledge Economy),Korea,under the ITRC(Information Technology Research Center)support programsupervised by the NIPA(National IT Industry Promotion Agency)(NIPA-2011-C1090-1121-0010)
文摘This paper suggests a new algorithm to solve problems of the current retinex algorithm such as distortion of grey out and color noise due to the individual treatment of RGB channel and log function,and halo effect occurred by use of the Gaussian filter.The current retinex algorithm treats each channel in RGB space that brings a phenomenon to change the rate of RGB.To improve this phenomenon,the color information was fixed in the HSV color space,and retinex treatment was conducted against the V value,a luminance feature.Linear treatment was carried out to remove color noise occurred by the use of log function.S value,a saturation value was compensated in proportion to the change of V value in luminance to obtain a clearer image.The proposed algorithm was evaluated against the landscape images that had strong backlit phenomena,and it is proved to have a better performance than the current retinex algorithm,multiscale retinex with cdor restoration(MSRCR).
