UM  > 科技學院
Differential evolutionary superpixel segmentation
Gong Y.-J.1; Zhou Y.2
2018-03-01
Source PublicationIEEE Transactions on Image Processing
ISSN10577149
Volume27Issue:3Pages:1390-1404
Abstract

Superpixel segmentation has been of increasing importance in many computer vision applications recently. To handle the problem, most state-of-the-art algorithms either adopt a local color variance model or a local optimization algorithm. This paper develops a new approach, named differential evolutionary superpixels, which is able to optimize the global properties of segmentation by means of a global optimizer. We design a comprehensive objective function aggregating within-superpixel error, boundary gradient, and a regularization term. Minimizing the within-superpixel error enforces the homogeneity of superpixels. In addition, the introduction of boundary gradient drives the superpixel boundaries to capture the natural image boundaries, so as to make each superpixel overlaps with a single object. The regularizer further encourages producing similarly sized superpixels that are friendly to human vision. The optimization is then accomplished by a powerful global optimizer'differential evolution. The algorithm constantly evolves the superpixels by mimicking the process of natural evolution, while using a linear complexity to the image size. Experimental results and comparisons with eleven state-ofthe- art peer algorithms verify the promising performance of our algorithm.

KeywordClustering Differential Evolution Preprocessing Seeding Superpixel Segmentation
DOI10.1109/TIP.2017.2778569
URLView the original
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000418863500014
全文获取链接
引用统计
被引频次[WOS]:10   [WOS记录]     [WOS相关记录]
Document TypeJournal article
专题Faculty of Science and Technology
DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Affiliation1.South China University of Technology
2.Universidade de Macau
推荐引用方式
GB/T 7714
Gong Y.-J.,Zhou Y.. Differential evolutionary superpixel segmentation[J]. IEEE Transactions on Image Processing,2018,27(3):1390-1404.
APA Gong Y.-J.,&Zhou Y..(2018).Differential evolutionary superpixel segmentation.IEEE Transactions on Image Processing,27(3),1390-1404.
MLA Gong Y.-J.,et al."Differential evolutionary superpixel segmentation".IEEE Transactions on Image Processing 27.3(2018):1390-1404.
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
Google Scholar
中相似的文章 Google Scholar
[Gong Y.-J.]的文章
[Zhou Y.]的文章
Baidu academic
中相似的文章 Baidu academic
[Gong Y.-J.]的文章
[Zhou Y.]的文章
Bing Scholar
中相似的文章 Bing Scholar
[Gong Y.-J.]的文章
[Zhou Y.]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。