A fast hybrid retargeting scheme with seam context and content aware strip partition

doi:10.1016/j.neucom.2018.01.058

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	A fast hybrid retargeting scheme with seam context and content aware strip partition
	Wu, Lifang 1; Yan, Chuncan 1; Jian, Meng 1; Liu, Shuang 1; Dong, Weiming2 ; Chen, Chang Wen 3
刊名	NEUROCOMPUTING
	2018-04-19
卷号	286 页码:198-213
关键词	Non-continuous Seam Carving Seam Context Content Aware Strip Partition Seam Distribution Fast Content Aware Image Distance
DOI	10.1016/j.neucom.2018.01.058
文献子类	Article
英文摘要	Image retargeting as a basic trick has been successfully applied to various computer vision problems. In this work, we propose a fast non-continuous seam carving with seam context (FN2SC) for robust and efficient image retargeting. FN2SC first conducts content aware image partition to separate an image into several strips with different tar get sizes from their content importance. It helps the removed seams in key objects distribute in a relatively uniform manner and prevents distortions to key objects. Then FN2SC performs fast non-continuous seam carving controlled by seam context of both neighboring relationship and touch bound relationship of seams. The seam context makes the removed seams distribute scattered and relieves artifacts caused by seam carving. During seam carving, image distortion is monitored by fast content aware image distance. Finally, FN2SC switches seam carving to scaling when the distortion meets the tolerance, which resizes the strips to the target sizes for image retargeting. Specifically, fast seam searching and image distortion based switching make FN2SC a fast and effective hybrid scheme. Experimental results demonstrate that the proposed FN2SC approach achieves good performance in terms of image quality and efficiency comprehensively. (c) 2018 Elsevier B.V. All rights reserved.
WOS关键词	QUALITY ASSESSMENT ; STRUCTURAL SIMILARITY ; SALIENCY DETECTION ; ADAPTIVE IMAGE ; MODEL
WOS研究方向	Computer Science
语种	英语
WOS记录号	WOS:000426425700019
资助机构	Beijing Municipal Education Commission Science and Technology Innovation Project(KZ201610005012) ; National Natural Science Foundation of China(61702022) ; China Postdoctoral Science Foundation(2017M610026) ; Beijing Postdoctoral Research Foundation(2017-ZZ-032)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/21980]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
作者单位	1.Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.SUNY Buffalo, Dept Comp Sci & Engn, Buffalo, NY USA
推荐引用方式 GB/T 7714	Wu, Lifang,Yan, Chuncan,Jian, Meng,et al. A fast hybrid retargeting scheme with seam context and content aware strip partition[J]. NEUROCOMPUTING,2018,286:198-213.
APA	Wu, Lifang,Yan, Chuncan,Jian, Meng,Liu, Shuang,Dong, Weiming,&Chen, Chang Wen.(2018).A fast hybrid retargeting scheme with seam context and content aware strip partition.NEUROCOMPUTING,286,198-213.
MLA	Wu, Lifang,et al."A fast hybrid retargeting scheme with seam context and content aware strip partition".NEUROCOMPUTING 286(2018):198-213.