OPT OpenIR  > 光学影像学习与分析中心
Perceptually Aware Image Retargeting for Mobile Devices
Zhou, Yinzuo1; Zhang, Luming2; Zhang, Chao3; Li, Ping4,5; Li, Xuelong6
Department光学影像学习与分析中心
2018-05-01
Source PublicationIEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN1057-7149
Volume27Issue:5Pages:2301-2313
Contribution Rank6
Abstract

Retargeting aims at adapting an original high-resolution photograph/video to a low-resolution screen with an arbitrary aspect ratio. Conventional approaches are generally based on desktop PCs, since the computation might be intolerable for mobile platforms (especially when retargeting videos). Typically, only low-level visual features are exploited, and human visual perception is not well encoded. In this paper, we propose a novel retargeting framework that rapidly shrinks a photograph/video by leveraging human gaze behavior. Specifically, we first derive a geometry-preserving graph ranking algorithm, which efficiently selects a few salient object patches to mimic the human gaze shifting path (GSP) when viewing a scene. Afterward, an aggregation-based CNN is developed to hierarchically learn the deep representation for each GSP. Based on this, a probabilistic model is developed to learn the priors of the training photographs that are marked as aesthetically pleasing by professional photographers. We utilize the learned priors to efficiently shrink the corresponding GSP of a retargeted photograph/video to maximize its similarity to those from the training photographs. Extensive experiments have demonstrated that: 1) our method requires less than 35 ms to retarget a 1024x768 photograph (or a 1280x720 video frame) on popular iOS/Android devices, which is orders of magnitude faster than the conventional retargeting algorithms; 2) the retargeted photographs/videos produced by our method significantly outperform those of its competitors based on a paired-comparison-based user study; and 3) the learned GSPs are highly indicative of human visual attention according to the human eye tracking experiments.

 

KeywordMobile Platform Retarget Perceptual Gaze Behavior Deep Feature Probabilistic Model
DOI10.1109/TIP.2017.2779272
Indexed BySCI ; EI
Language英语
WOS IDWOS:000426272000017
EI Accession Number20175004537170
Citation statistics
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/30766
Collection光学影像学习与分析中心
Affiliation1.Hangzhou Normal Univ, Alibaba Res Ctr Complex Sci, Hangzhou 311121, Zhejiang, Peoples R China;
2.Zhejiang Univ, Coll Comp Sci, Hangzhou 310000, Zhejiang, Peoples R China;
3.Univ Illinois, Comp Sci Dept, Champaign, IL 61820 USA;
4.Hangzhou Dianzi Univ, Sch Comp Sci & Technol, Hangzhou 310018, Zhejiang, Peoples R China;
5.Nanjing Univ, State Key Lab Novel Software Technol, Nanjing 210093, Jiangsu, Peoples R China;
6.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr OPT IMagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian 710119, Shaanxi, Peoples R China
Recommended Citation
GB/T 7714
Zhou, Yinzuo,Zhang, Luming,Zhang, Chao,et al. Perceptually Aware Image Retargeting for Mobile Devices[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2018,27(5):2301-2313.
APA Zhou, Yinzuo,Zhang, Luming,Zhang, Chao,Li, Ping,&Li, Xuelong.(2018).Perceptually Aware Image Retargeting for Mobile Devices.IEEE TRANSACTIONS ON IMAGE PROCESSING,27(5),2301-2313.
MLA Zhou, Yinzuo,et al."Perceptually Aware Image Retargeting for Mobile Devices".IEEE TRANSACTIONS ON IMAGE PROCESSING 27.5(2018):2301-2313.
Files in This Item:
File Name/Size DocType Version Access License
Perceptually Aware I(3015KB)期刊论文出版稿限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhou, Yinzuo]'s Articles
[Zhang, Luming]'s Articles
[Zhang, Chao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhou, Yinzuo]'s Articles
[Zhang, Luming]'s Articles
[Zhang, Chao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhou, Yinzuo]'s Articles
[Zhang, Luming]'s Articles
[Zhang, Chao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.