Change search
ReferencesLink to record
Permanent link

Direct link
Modeling Image Context using Object Centered Grid
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
2009 (English)In: 2009 DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA 2009), NEW YORK: IEEE , 2009, 476-483 p.Conference paper (Refereed)
Abstract [en]

Context plays a valuable role in any image understanding task confirmed by numerous studies which have shown the importance of contextual information in computer vision tasks, like object detection, scene classification and image retrieval. Studies of human perception on the tasks of scene classification and visual search have shown that human visual system makes extensive use of contextual information as post-processing in order to index objects. Several recent computer vision approaches use contextual information to improve object recognition performance. They mainly use global information of the whole image by dividing the image into several pre-defined subregions, so called fixed grid. In this paper we propose an alternative approach to retrieval of contextual information, by customizing the location of the grid based on salient objects in the image. We claim this approach to result in more informative contextual features compared to the fixed-grid based strategy. To compare our results with the most relevant and recent papers, we use PASCAL 2007 data set. Our experimental results show an improvement in terms of Mean Average Precision.

Place, publisher, year, edition, pages
NEW YORK: IEEE , 2009. 476-483 p.
Keyword [en]
Context, Scene, Histogram, Bag-of-Features
National Category
Computer Engineering
URN: urn:nbn:se:kth:diva-34251DOI: 10.1109/DICTA.2009.80ISI: 000290469200069ScopusID: 2-s2.0-77950315041ISBN: 978-1-4244-5297-2OAI: diva2:422476
Digital Image Computing: Techniques and Applications, DICTA 2009; Melbourne
QC 20110613Available from: 2011-06-13 Created: 2011-05-30 Last updated: 2011-06-13Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Parizi, Sobhan NaderiLaptev, IvanTarghi, Alireza Tavakoli
By organisation
Computer Vision and Active Perception, CVAP
Computer Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 22 hits
ReferencesLink to record
Permanent link

Direct link