梯度稀疏性先验图像matting算法  

Image Matting Using Gradient Sparsity Prior

作　　者：李晋江[1,2] 苑根基 范辉[1,2] LI Jin-jiang;YUAN Gen-ji;FAN Hui(School of Computer Science and Technology,Shandong Technology and Business University,Yantai 264000,China;Co-innovation Center of Shandong Colleges and Universities,Future Intelligent Computing,Shandong Technology and Business University,Yantai 264000,China)

机构地区：[1]山东工商学院计算机科学与技术学院,山东烟台264000 [2]山东工商学院山东省高等学校协同创新中心未来智能计算,山东烟台264000

出　　处：《小型微型计算机系统》2018年第11期2551-2556,共6页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61472227,61772319,61602277,61773244)资助.

摘　　要：结构复杂的背景以及模糊的前景/背景界限是matting所面临的挑战.复杂的纹理使得想要精确的提取前景对象变得困难.本文利用梯度稀疏先验,将图像分为两层处理,并将两层的梯度正则化,使一层具有长尾分布,另一层具有短尾分布.两层图像的梯度不具有一致性,其中一层的梯度小于另一层的梯度.舍弃复杂纹理的图层,使背景复杂的纹理得到抑制,并且使前景对象变得平滑,前景/背景之间的界限更为清晰.对matting结果进行定性比较和定量分析,实验表明,利用梯度稀疏先验对图像进行处理,可以得到精度更高的alpha遮罩.The complex structure of the background and the blurred foreground/background boundaries are the challenges that the matting faces.Complex textures make it difficult to accurately extract foreground objects.We use gradient sparse priors to divide the image into two layers and normalize the gradient of the two layers so that one layer has a long tail and the other has a short tail.The gradient of the two-layer image does not have consistency.One of the gradients is less than the other.We discard the layers that contain complex textures of the image,suppress the textures with complex backgrounds,and smooth the foreground objects.The boundary between foreground/background is clearer.We use a qualitative comparison and quantitative analysis of the matting results.Experiments have shown that we can get a higher-accuracy alpha mask by processing the image with gradient sparse priors.

关 键 词：梯度稀疏 梯度正则化 图层 图像抠图 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]