Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/80983
Title: Scene recognition by semantic visual words
Authors: Farahzadeh, Elahe
Sluzek, Andrzej
Cham Tat Jen (SCE)
Keywords: Scene recognition
Semantic vocabulary
Visual words
Issue Date: 2014
Source: Farahzadeh, E., Cham, T. J., & Sluzek, A. (2015). Scene recognition by semantic visual words. Signal, Image and Video Processing, 9(8), 1935-1944.
Series/Report no.: Signal, Image and Video Processing
Abstract: In this paper, we propose a novel approach to introduce semantic relations into the bag-of-words framework. We use the latent semantic models, such as latent semantic analysis (LSA) and probabilistic latent semantic analysis (pLSA), in order to define semantically rich features and embed the visual features into a semantic space. The semantic features used in LSA technique are derived from the low-rank approximation of word–image occurrence matrix by singular value decomposition. Similarly, by using the pLSA approach, the topic-specific distributions of words can be considered dimensions of a concept space. In the proposed space, the distances between words represent the semantic distances which are used for constructing a discriminative and semantically meaningful vocabulary. Position information significantly improves scene recognition accuracy. Inspired by this, in this paper, we bring position information into the proposed semantic vocabulary frameworks. We have tested our approach on the 15-Scene and 67-MIT Indoor datasets and have achieved very promising results.
URI: https://hdl.handle.net/10356/80983
http://hdl.handle.net/10220/38975
ISSN: 1863-1703
DOI: 10.1007/s11760-014-0687-7
Schools: School of Computer Engineering 
Research Centres: Centre for Computational Intelligence 
Centre for Multimedia and Network Technology 
Rights: © 2014 Springer-Verlag London. This is the author created version of a work that has been peer reviewed and accepted for publication by Signal, Image and Video Processing, Springer-Verlag London. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [http://dx.doi.org/10.1007/s11760-014-0687-7].
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
Scene recognition by semantic visual words.pdf3.16 MBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations 50

3
Updated on Jun 22, 2024

Web of ScienceTM
Citations 50

2
Updated on Oct 30, 2023

Page view(s) 50

456
Updated on Jun 22, 2024

Download(s) 20

290
Updated on Jun 22, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.