中文|CAS

logo
banner

Journals & Publications

Journals Publications Papers

Papers

Adaptive Content Condensation Based on Grid Optimization for Thumbnail Image Generation
Dec 16, 2016Author：
PrintText Size A A

Title: Adaptive Content Condensation Based on Grid Optimization for Thumbnail Image Generation
Authors: Wang, JQ; Qu, Z; Chen, YY; Mei, T; Xu, M; Zhang, L; Lu, HQ
Author Full Names: Wang, Jinqiao; Qu, Zhan; Chen, Yingying; Mei, Tao; Xu, Min; Zhang, La; Lu, Hanqing
Source: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 26 (11):2079-2092; 10.1109/TCSVT.2015.2493500 NOV 2016
Language: English
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.
ISSN: 1051-8215
eISSN: 1558-2205
IDS Number: EC1US
Unique ID: WOS:000387894100008
*Click Here to View Full Record