色外观匹配的高动态范围图像再现  

High Dynamic Range Image Reproduction Based on Color Appearance Mapping

作　　者：罗雪梅[1] 王义峰[1] 曾平[1,2] 郑海红[1] 

机构地区：[1]西安电子科技大学计算机学院,西安710071 [2]西安石油大学计算机学院,西安710065

出　　处：《计算机研究与发展》2013年第8期1787-1796,共10页Journal of Computer Research and Development

基　　金：国家部委"十二五"预研基金项目(513160702);国家自然科学基金项目(J0500100306;61173025);国家部委预研基金项目(9140A16050109DZ01);中央高校基本科研业务费专项基金项目(K5051303014)

摘　　要：针对高动态范围(high dynamic range,HDR)图像再现因观察条件变化引起的再现图像与源图像色外观不一致问题,提出一种色外观匹配的HDR图像再现算法.首先将HDR图像的色度和亮度信息分离,通过估计源场景观察条件,利用色外观模型(color appearance model,CAM)将HDR图像再现至显示环境,保持源场景的色度外观;然后针对亮度图像,根据直方图特征进行自适应分区,构造分段线性色阶调整函数,将显示亮度范围动态分配给不同的亮度分区,以增强图像感知对比度,并利用双边滤波技术提取图像细节信息进行细节补偿;最后,将处理后的彩色和非彩色信息合成,并对亮度压缩带来的色外观变化进行色度校正,得到与源HDR图像色外观一致的低动态范围(low dynamic range,LDR)再现图像.实验表明,新算法在色外观保持、动态范围压缩和细节表现上均优于传统算法.To solve the problem that different viewing conditions results in different color appearance between a reproduced image and its original one during high dynamic range （HDR） image reproduction, a new algorithm based on color appearance mapping for HDR image reproduction is presented. Firstly, the chrominance and luminance of the HDR image are processed separately, through the estimation of the original environment parameters, the HDR image is reproduced under the display environment by a color appearance model, which preserves the chromatic appearance across scene and display environments. Then the luminance image is regionalized adaptively according to the histogram characteristics, and a piecewise linear tone scale function is constructed to allocate the range of display luminance for different regions dynamically, which raises perceptual contrast of the image. Meanwhile, the details of the luminance image is extracted through bilateral filtering technology in order to maintain details. Finally, the processed chromatic and achromatic image is synthesized and the change of color appearance affected by luminance compressing is corrected, and then the reproduced low dynamic range image is obtained, which is mapped in color appearance with the original HDR image. Experiments show that the proposed algorithm gains advantages over the traditional ones in color appearance maintaining, dynamic range compressing, and the performance of details.

关 键 词：HDR图像 色阶映射 色外观匹配 观察条件估计 自适应分区 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]