Adaptive patch size determination for patch-based image completion

Zhou, Hailing and Zheng, Jianmin 2010, Adaptive patch size determination for patch-based image completion, in ICIP 2010 : Proceedings of the 17th IEEE International Conference on Image Processing, IEEE Computer Society, Los Alamitos, Calif., pp. 421-424.

Attached Files
Name Description MIMEType Size Downloads

Title Adaptive patch size determination for patch-based image completion
Author(s) Zhou, Hailing
Zheng, Jianmin
Conference name International Conference on Image Processing (17th : 2010 : Hong Kong, China)
Conference location Hong Kong, China
Conference dates 26-29 Sep. 2010
Title of proceedings ICIP 2010 : Proceedings of the 17th IEEE International Conference on Image Processing
Editor(s) [Unknown]
Publication date 2010
Conference series International Conference on Image Processing
Start page 421
End page 424
Total pages 4
Publisher IEEE Computer Society
Place of publication Los Alamitos, Calif.
Keyword(s) adaptive patch size
image completion
region filling
Summary Patch-based image completion proceeds by iteratively filling the target (unknown) region by the best matching patches in the source image. In most existing such algorithms, the size of the patches is either fixed and specified by a default number or simply chosen to be inversely proportional to the spatial frequency. However, it is noted that the patch size affects how well the filled patch captures the local characteristics of the source image and thus the final completion accuracy. Thus in this paper we propose a new method to compute appropriate patch sizes for image completion to improve its performance. In particular, we formulate the patch size determination as an optimization problem that minimizes an objective function involving image gradients and distinct and homogenous features. Experimental results show that our method can provide a significant enhancement to patch-based image completion algorithms.
ISBN 1424479932
9781424479931
ISSN 1522-4880
Language eng
Field of Research 080103 Computer Graphics
080104 Computer Vision
080106 Image Processing
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1.1 Full written paper - refereed
Persistent URL http://hdl.handle.net/10536/DRO/DU:30049235

Document type: Conference Paper
Collection: Centre for Intelligent Systems Research
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 3 times in TR Web of Science
Scopus Citation Count Cited 2 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 50 Abstract Views, 4 File Downloads  -  Detailed Statistics
Created: Thu, 01 Nov 2012, 13:12:48 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.