改进金字塔融合技术的低照度图像色彩恢复和细节提取
|
摘要
针对低照度图像亮度大、色彩不均衡的现象进行了改进金字塔融合技术的低照度图像色彩恢复算子的研究。该算法将原图和用去雾模型或MSRCR改善后的预处理图用金子塔技术将色彩对比度、饱和度、曝光亮度三者融合到金字塔算法中,并根据图像的信息赋予了不同的权重参数,从而能够有效地解决传统低照度图像色彩增强存在的问题。提出一种CIELAB通道内用加权最小二乘数的保边平滑滤波器平滑L通道的图像,设置不同的色调映射的参数值来提升图像细节信息的算子,使夜视中图像的信息更显眼和真实。实验结果表明,所提算法在低照度图像色彩增强中有了很好的效果,并在信息熵和PSNR评价取得了约10%的质量提升。所选择三种不同类型的图像进行实验,图形质量都得到了提高,也表明所提算法具有一定普适性。
Aiming at the phenomenon that the low luminance image is bright and the the color is not balanced,this paper had carried on the study of the color recovery operator of the low illumination image with improved pyramid fusion technology. The algorithm combined the original image and the pretreatment diagram with the defog model or MSRCR to fuse the color contrast,saturation and brightness into the pyramid algorithm with the gold tower technique,and assigned different weight parameters according to the information of the image,which could effectively solve the traditional low-light image color enhancement problems. And it proposed a Fourier smoothing filter with weighted least squares in the CIELAB channel to smooth the image of the L channel,set the parameters of different tone mapping to enhance the image detail information,so that the information of the image in night vision is more Conspicuous and true. It selected three different types of images for experimentation,and improved the quality of graphics. It also shows that this algorithm has some universality.
Aiming at the phenomenon that the low luminance image is bright and the the color is not balanced,this paper had carried on the study of the color recovery operator of the low illumination image with improved pyramid fusion technology. The algorithm combined the original image and the pretreatment diagram with the defog model or MSRCR to fuse the color contrast,saturation and brightness into the pyramid algorithm with the gold tower technique,and assigned different weight parameters according to the information of the image,which could effectively solve the traditional low-light image color enhancement problems. And it proposed a Fourier smoothing filter with weighted least squares in the CIELAB channel to smooth the image of the L channel,set the parameters of different tone mapping to enhance the image detail information,so that the information of the image in night vision is more Conspicuous and true. It selected three different types of images for experimentation,and improved the quality of graphics. It also shows that this algorithm has some universality.
引文
[1] Zhou Zhigang,Sang Nong,Hu Xinrong. Global brightness and local contrast adaptive enhancement for low illumination color image[J].Optik-International Journal for Light and Electron Optics,2014,125(6):1795-1799.
[2] Mccann J J,Rizzi A. Retinex algorithms[M]//The Art and Science of HDR Imaging. New York:Wiley,2011:293-340.
[3] Jobson D J,Rahman Z,Woodell G A. A multiscale Retinex for bridging the gap between color images and the human observation of scenes[J].IEEE Trans on Image Processing,1997,6(7):965-976.
[4] Wang Wen,Li Bo,Zheng Jin,et al. A fast multi-scale Retinex algorithm for color image enhancement[C]//Proc of IEEE International Conference on Wavelet Analysis and Pattern Recognition. Piscataway,NJ:IEEE Press,2008:80-85.
[5] Xie Bin,Guo Fan,Cai Zixing. Improved single image dehazing using dark channel prior and multi-scale retinex[C]//Proc of IEEE International Conference on Intelligent System Design and Engineering Application. Piscataway,NJ:IEEE Press,2010:848-851.
[6] Lee H G,Yang S,Sim J Y. Color preserving contrast enhancement for low light level images based on Retinex[C]//Proc of IEEE Asia-Pacific Signal and Information Processing Association Summit and Conference. Piscataway,NJ:IEEE Press,2015:884-887.
[7] Li Lin,Wang Ronggang,Wang Wenmin,et al. A low-light image enhancement method for both denoising and contrast enlarging[C]//Proc of IEEE International Conference on Image Processing. Piscataway,NJ:IEEE Press,2015:3730-3734.
[8] Su Haonan,Jung C. Low light image enhancement based on two-step noise suppression[C]//Proc of IEEE International Conference on Acoustics,Speech and Signal Processing. Piscataway,NJ:IEEE Press,2017:1977-1981.
[9] Dong Xuan,Wang Guan,Pang Yi,et al. Fast efficient algorithm for enhancement of low lighting video[C]//Proc of IEEE International Conference on Multimedia and Expo. Piscataway,NJ:IEEE Press,2011:1-6.
[10]王小元,张红英,吴亚东,等.基于物理模型的低照度图像增强算法[J].计算机应用,2015,35(8):2301-2304.(Wang Xiaoyuan,Zhang Hongying,Wu Yadong,et al. Low-light image enhancement algorithm based on physical model[J]. Journal of Computer Applications,2015,35(8):2301-2304.)
[11] Burt P J,Adelson E H. The Laplacian pyramid as a compact image code[M]//Readings in Computer Vision:Issues,Problems,Principles,and Paradigms. San Francisco:Morgan Kaufmann Publishers Inc.,1987:671-679.
[12]Burt P J. The pyramid as a structure for efficient computation[M]//Multiresolution Image Processing and Analysis. Berlin:Springer,1984:6-35.
[13]Mertens T,Kautz J,Reeth F V. Exposure fusion:a simple and practical alternative to high dynamic range photography[J]. Computer Graphics Forum,2010,28(1):161-171.
[14]Singh H,Kumar V,Bhooshan S. A novel approach for detail-enhanced exposure fusion using guided filter[J/OL]. The Scientific World Journal,2014(2):659217.(2014-02-09). http://dx. doi. org/10.1155/2014/659217.
[2] Mccann J J,Rizzi A. Retinex algorithms[M]//The Art and Science of HDR Imaging. New York:Wiley,2011:293-340.
[3] Jobson D J,Rahman Z,Woodell G A. A multiscale Retinex for bridging the gap between color images and the human observation of scenes[J].IEEE Trans on Image Processing,1997,6(7):965-976.
[4] Wang Wen,Li Bo,Zheng Jin,et al. A fast multi-scale Retinex algorithm for color image enhancement[C]//Proc of IEEE International Conference on Wavelet Analysis and Pattern Recognition. Piscataway,NJ:IEEE Press,2008:80-85.
[5] Xie Bin,Guo Fan,Cai Zixing. Improved single image dehazing using dark channel prior and multi-scale retinex[C]//Proc of IEEE International Conference on Intelligent System Design and Engineering Application. Piscataway,NJ:IEEE Press,2010:848-851.
[6] Lee H G,Yang S,Sim J Y. Color preserving contrast enhancement for low light level images based on Retinex[C]//Proc of IEEE Asia-Pacific Signal and Information Processing Association Summit and Conference. Piscataway,NJ:IEEE Press,2015:884-887.
[7] Li Lin,Wang Ronggang,Wang Wenmin,et al. A low-light image enhancement method for both denoising and contrast enlarging[C]//Proc of IEEE International Conference on Image Processing. Piscataway,NJ:IEEE Press,2015:3730-3734.
[8] Su Haonan,Jung C. Low light image enhancement based on two-step noise suppression[C]//Proc of IEEE International Conference on Acoustics,Speech and Signal Processing. Piscataway,NJ:IEEE Press,2017:1977-1981.
[9] Dong Xuan,Wang Guan,Pang Yi,et al. Fast efficient algorithm for enhancement of low lighting video[C]//Proc of IEEE International Conference on Multimedia and Expo. Piscataway,NJ:IEEE Press,2011:1-6.
[10]王小元,张红英,吴亚东,等.基于物理模型的低照度图像增强算法[J].计算机应用,2015,35(8):2301-2304.(Wang Xiaoyuan,Zhang Hongying,Wu Yadong,et al. Low-light image enhancement algorithm based on physical model[J]. Journal of Computer Applications,2015,35(8):2301-2304.)
[11] Burt P J,Adelson E H. The Laplacian pyramid as a compact image code[M]//Readings in Computer Vision:Issues,Problems,Principles,and Paradigms. San Francisco:Morgan Kaufmann Publishers Inc.,1987:671-679.
[12]Burt P J. The pyramid as a structure for efficient computation[M]//Multiresolution Image Processing and Analysis. Berlin:Springer,1984:6-35.
[13]Mertens T,Kautz J,Reeth F V. Exposure fusion:a simple and practical alternative to high dynamic range photography[J]. Computer Graphics Forum,2010,28(1):161-171.
[14]Singh H,Kumar V,Bhooshan S. A novel approach for detail-enhanced exposure fusion using guided filter[J/OL]. The Scientific World Journal,2014(2):659217.(2014-02-09). http://dx. doi. org/10.1155/2014/659217.