期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 27, 期 6, 页码 2883-2896出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2018.2810541
关键词
Content-adaption; discriminability; pre-processing; superpixel
资金
- National Natural Science Foundation of China [61502542]
- Macau Science and Technology Development Fund [FDCT/016/2015/A1]
- Research Committee at the University of Macau [MYRG2016-00123-FST]
Superpixel segmentation targets at grouping pixels in an image into atomic regions whose boundaries align well with the natural object boundaries. This paper first proposes a new feature representation for superpixel segmentation that holistically embraces color, contour, texture, and spatial features. Then, we introduce a clustering-based discriminability measure to iteratively evaluate the importance of different features. Integrating the feature representation and the discriminability measure, we propose a novel content-adaptive superpixel (CAS) segmentation algorithm. CAS is able to automatically and iteratively adjust the weights of different features to fit various properties of image instances. Experiments on several challenging datasets demonstrate that the proposed CAS outperforms the state-of-the-art methods and has a low computational cost.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据