QQ客服 官方微博 反馈留言

	CONNECTIVITY SIMILARITY BASED TRANSDUCTIVE LEARNING FOR INTERACTIVE IMAGE SEGMENTATION
	Mu, Yadong ; Zhou, Bingfeng
	2009
关键词	interactive image segmentation connectivity similarity linear propagation
英文摘要	We propose a novel graph-based transductive learning approach for interactive image segmentation. Here the term "transductive" indicates a process that iteratively propagates information from user-labeled regions to unlabeled image pixels. For the application of interactive image segmentation, transductive approach has several advantages compared with traditional color probabilistic model based approach. However, previous transductive approaches for image segmentation usually utilize an 8-connected neighborhood system, which has low efficacy when transferring local information to remote pixels. The main contribution of this paper is to estimate pairwise pixel similarity based on a novel path-based metric (i.e. connectivity similarity), rather than local comparison with 8-connected neighbors. We further theoretically prove the computing complexity is on a polynomial order and provide convergence guarantee for the extra local smoothing operation that is introduced to further refine the initial results. Especially, the proposed method shows promising performance in the multi-label case. Various experiments are presented to illustrate its effectiveness.; http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000268919200309&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=8e1609b174ce4e31116a60747a720701 ; Acoustics; Engineering, Electrical & Electronic; EI; CPCI-S(ISTP); 0
语种	英语
DOI标识	10.1109/ICASSP.2009.4959813
内容类型	其他
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/162000]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Mu, Yadong,Zhou, Bingfeng. CONNECTIVITY SIMILARITY BASED TRANSDUCTIVE LEARNING FOR INTERACTIVE IMAGE SEGMENTATION. 2009-01-01.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

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。