Please use this identifier to cite or link to this item:
Title: A hybrid holistic/semantic approach for scene classification
Authors: Chen, Z
Chi, Z 
Fu, H
Keywords: Holistic representation
Scene classification
Semantic representation
Semantic spatial pyramid
Issue Date: 2014
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Proceedings - International Conference on Pattern Recognition, 2014, 6977111, p. 2299-2304 How to cite?
Abstract: There are two main strategies to tackle scene classification: holistic and semantic. The former characterizes a scene using its global features, while the latter represents a scene by modeling its internal object configuration. Holistic strategy is good at representing scenes with simple contents, but it does not represent well complex scenes that consist of multiple objects. By contrast, semantic strategy is advantageous at recognizing scenes with complex objects, but it does not work well for simple scenes. In this paper, we propose to integrate holistic and semantic strategies to cope with scene classification. In particular, we exploit a deep learning algorithm to learn features for scene representation in the holistic way. For the semantic strategy, we explore a semantic spatial pyramid to represent the spatial object configuration of scenes. The holistic and semantic strategies are integrated using a method proposed by us. Experimental results on a benchmark natural scene dataset demonstrate the effectiveness of our proposed hybrid approach for scene classification, by comparing to several state-of-the-art algorithms.
Description: 22nd International Conference on Pattern Recognition, ICPR 2014, Sweden, 24-28 August 2014
ISBN: 978-1-4799-5209-0 (electronic)
978-1-4799-5210-6 (print on demand (PoD))
ISSN: 1051-4651
DOI: 10.1109/ICPR.2014.399
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Aug 14, 2017

Page view(s)

Last Week
Last month
Checked on Aug 20, 2017

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.