Journal article
Optimal multiple-seams search for image resizing with smoothness and shape prior
The Visual computer, Vol.26(6), pp.749-759
06/2010
DOI: 10.1007/s00371-010-0480-8
Abstract
Content-aware image resizing is of increasing relevance to allow high-quality image and video to be displayed on devices with different resolution. We present a novel method to find multiple seams simultaneously with global optimality for image resizing, incorporating both region smoothness and seam shape prior using a 3-D graph-theoretic approach. The globally optimal seams can be simultaneously achieved by solving a maximum flow problem based on an arc-weighted graph representation. Representing the resizing problem in an arc-weighted graph, we can incorporate a wide spectrum of constraints into the formulation, thus improving resizing results. By removing or inserting those multiple seams, the goal of content-aware image resizing is achieved. Due to simultaneous detection of multiple seams, our algorithm exhibits several good features: the ability to handle both crossing and non-crossing-seam cases, the ability to incorporate various feasible geometry constraints, and the ability to incorporate the seams importance, region smoothness and shape prior information. The proposed method was implemented and experimented on a variety of image data and compared with the state of the art in image resizing.
Details
- Title: Subtitle
- Optimal multiple-seams search for image resizing with smoothness and shape prior
- Creators
- Dongfeng Han - Department of Radiation Oncology The University of Iowa Iowa City IA USAMilan Sonka - Department of Electrical and Computer Engineering The University of Iowa Iowa City IA USAJohn Bayouth - Department of Radiation Oncology The University of Iowa Iowa City IA USAXiaodong Wu - Department of Electrical and Computer Engineering The University of Iowa Iowa City IA USA
- Resource Type
- Journal article
- Publication Details
- The Visual computer, Vol.26(6), pp.749-759
- DOI
- 10.1007/s00371-010-0480-8
- ISSN
- 0178-2789
- eISSN
- 1432-2315
- Publisher
- Springer-Verlag; Berlin/Heidelberg
- Language
- English
- Date published
- 06/2010
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; Injury Prevention Research Center; Ophthalmology and Visual Sciences
- Record Identifier
- 9984046921202771
Metrics
29 Record Views