Abstract: This paper presents an efficient algorithm for alpha estimation based on perceptual color space in natural image matting. A user specifies a trimap which partitions an image into definitely foreground, definitely background and unknown. For each pixel in the unknown region, the algorithm separates intensity and chroma information from RGB color after its foreground and background color components are estimated. Alpha component is decomposed into intensity part and chroma part. The weighted mean of these two parts yields the final alpha value.

Key words: blue screen matting, natural image matting, alpha, perceptual color space

摘要： 提出一种用于自然图像抠图的高效的基于感知颜色空间的透明度估计方法。在用户指定图像的未知区域后，对于其中的任意一点，估计出该点的前景颜色分量和背景颜色分量，把该点RGB颜色的亮度信息和色度信息分开。分别估计出该点的亮度透明度分量和色度透明度分量，将这2个透明度分量的加权平均作为该点的最终透明度值。

关键词: 蓝屏抠图, 自然图像抠图, 透明度, 感知颜色空间

CLC Number: 

• TP391