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

doi:10.1016/j.neucom.2018.01.058

	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
发表期刊	NEUROCOMPUTING
	2018-04-19
卷号	286 页码:198-213
文章类型	Article
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.
关键词	Non-continuous Seam Carving Seam Context Content Aware Strip Partition Seam Distribution Fast Content Aware Image Distance
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.neucom.2018.01.058
关键词[WOS]	QUALITY ASSESSMENT ; STRUCTURAL SIMILARITY ; SALIENCY DETECTION ; ADAPTIVE IMAGE ; MODEL
收录类别	SCI
语种	英语
项目资助者	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)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000426425700019
引用统计	被引频次：4[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/21980
专题	多模态人工智能系统全国重点实验室_多媒体计算
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.