Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
| Adaptive Content Condensation Based on Grid Optimization for Thumbnail Image Generation | |
Wang, Jinqiao1 ; Qu, Zhan2; Chen, Yingying1; Mei, Tao3; Xu, Min4; Zhang, La1; Lu, Hanqing1; Jinqiao Wang
| |
| Source Publication | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 2016-11-01 | |
| Volume | 26Issue:11Pages:2079-2092 |
| Subtype | Article |
| Abstract | An ideal thumbnail generator should effectively condense unimportant regions and keep the important content undeformed, completed, and at a proper scale, i.e., accuracy, completeness, and sufficiency. Each retargeting method has its own advantage for resizing arbitrary images. However, they often ignore the completeness and sufficiency for information presentation in thumbnails. In this paper, we formulate thumbnail generation as an image content condensation problem and propose a unified grid optimization framework to fuse multiple operators. From the view of accuracy, completeness, and sufficiency for information presentation, we exploit complementary relationships among three condensation operators and fuse them into a unified grid-based convex programming problem, which could be solved simultaneously and efficiently through numerical optimization. Besides warping energy to preserve the geometric structure of important objects, we put forward two grid-based energy terms to keep the completeness of important objects and retain them at a proper size. Finally, an adaptive procedure is proposed to dynamically adjust the contribution of loss functions for achieving optimal content condensation. Both qualitative and quantitative comparison results demonstrate that the proposed method achieves an excellent tradeoff among accuracy, completeness, and sufficiency of information preservation. The experimental results show that our approach is obviously superior to the state-of-the-art techniques. |
| Keyword | Image Browsing Image Resizing Image Retargeting Thumbnail Generation |
| WOS Headings | Science & Technology ; Technology |
| DOI | 10.1109/TCSVT.2015.2493500 |
| WOS Keyword | SALIENT REGION DETECTION ; QUALITY ASSESSMENT ; MODEL |
| Indexed By | SCI |
| Language | 英语 |
| Funding Organization | 863 Program(2014AA015104) ; National Natural Science Foundation of China(61273034 ; 61332016) |
| WOS Research Area | Engineering |
| WOS Subject | Engineering, Electrical & Electronic |
| WOS ID | WOS:000387894100008 |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.ia.ac.cn/handle/173211/11073 |
| Collection | 模式识别国家重点实验室_图像与视频分析 |
| Corresponding Author | Jinqiao Wang |
| Affiliation | 1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.Huawei Technol Co Ltd, Media Lab, Shenzhen 518129, Peoples R China 3.Microsoft Res Asia, Beijing 100080, Peoples R China 4.Univ Technol Sydney, Global Big Data Technol Ctr, Sydney, NSW 2007, Australia |
| First Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
| Recommended Citation GB/T 7714 | Wang, Jinqiao,Qu, Zhan,Chen, Yingying,et al. Adaptive Content Condensation Based on Grid Optimization for Thumbnail Image Generation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2016,26(11):2079-2092. |
| APA | Wang, Jinqiao.,Qu, Zhan.,Chen, Yingying.,Mei, Tao.,Xu, Min.,...&Jinqiao Wang.(2016).Adaptive Content Condensation Based on Grid Optimization for Thumbnail Image Generation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,26(11),2079-2092. |
| MLA | Wang, Jinqiao,et al."Adaptive Content Condensation Based on Grid Optimization for Thumbnail Image Generation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 26.11(2016):2079-2092. |
| Files in This Item: | Download All | |||||
| File Name/Size | DocType | Version | Access | License | ||
| Adaptive Content Con（3335KB） | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | View Download | |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment