文献类型：期刊文献

中文题名：基于显著目标移动的自动抠图方法

英文题名：An Automatic Matting Method Based on Moving Saliency Objects

作者：陈志华[1];朱楠楠[1];肖小龙[1];张静[1,2];袁玉波[1]

机构：[1]华东理工大学计算机科学与工程系,上海200237;[2]南京大学计算机软件新技术国家重点实验室,江苏南京210093

年份：2015

卷号：36

期号：3

起止页码：425

中文期刊名：图学学报

外文期刊名：Journal of Graphics

收录：CSTPCD;;北大核心:【北大核心2014】；CSCD:【CSCD_E2015_2016】；

基金：国家自然科学基金资助项目(61370174;61402174)

语种：中文

中文关键词：图像显著性;显著目标移动;自动抠图

外文关键词：image saliency;moving saliency regions;automatic matting

摘要：抠图技术是一种常用的提取图像中精确目标区域的方法,在图像编辑中有着重要的应用,现有的大多数抠图技术依赖于人工交互,本文提出一种基于显著目标移动的自动抠图方法。首先对输入图像进行区域分割;然后计算各个区域的显著性值,并建立区域之间的显著性引力模型;在此基础上进行基于显著目标移动的迭代,从而获取图像的显著区域;之后对显著图进行分割并且进行目标区域形态学运算,生成三分图;最后利用基于学习的抠图算法,提取图像目标。实验结果表明,本文方法不需要人工交互和其他的辅助信息,目标抠取效果良好。
Matting technique is a popular method to extract objects from an image precisely. It takes important advantages in image editing. Most of the existing matting techniques rely on human interaction. In this paper, a novel automatic matting method is proposed and it is based on moving saliency objects. Firstly, the input image is segmented into several regions, its saliency values are calculated, a saliency gravitation model between regions is established, and the moving rules of saliency regions are constructed to obtain an accurate saliency map. Secondly, the saliency map is obtained and morphological operators are employed to correct the object regions. The corresponding trimap is generated automatically. Finally, the object regions are extracted by using learning-based matting algorithm. The experimental results show that the proposed method is more accurate and effective without human interaction or other auxiliary information.