Real-time contrast preserving decolorization
Real-time contrast preserving decolorization
复制标题
DOI：
10.1145/2407746.2407780
复制
发表时间：
2012-11
期刊：
影响因子：
--
通讯作者：
Cewu Lu;Li Xu;Jiaya Jia
中科院分区：
文献类型：
--
作者：
Cewu Lu;Li Xu;Jiaya Jia
脱色-将彩色图像转换为灰度图像的过程-是数字印刷、风格化黑白摄影以及许多单通道图像和视频处理应用程序中的基本工具。虽然最近的研究集中在保留有意义的视觉特征和颜色对比度上，但对转换的复杂性问题关注较少。因此，所得到的脱色方法可能比简单的程序(例如，MatLab内置的rgb2灰色函数)慢一个数量级，这可能会阻碍它们的实际使用。在本文中，我们提出了一种非常快速而有效的脱色方法。通过一种新的定量度量以及与最先进方法的定性比较，证明了该方法的有效性。
Decolorization -- the process to transform a color image to a grayscale one -- is a basic tool in digital printing, stylized black-and-white photography, and in many single channel image and video processing applications. While recent research focuses on retaining meaningful visual features and color contrast, less attention has been paid to the complexity issue of the conversion. Consequently, the resulting decolorization methods could be orders of magnitude slower than simple procedures, e.g., Matlab built-in rgb2gray function, which could hamper them from being used practically. In this paper, we propose a very fast and yet effective decolorization approach. The effectiveness of the method is borne out by a new quantitative metric as well as qualitative comparisons with state-of-the-art methods.