Please use this identifier to cite or link to this item:
Title: An image similarity descriptor for classification tasks
Authors: Wang, Liangliang
Rajan, Deepu
Keywords: Engineering::Computer science and engineering
Issue Date: 2020
Source: Wang, L. & Rajan, D. (2020). An image similarity descriptor for classification tasks. Journal of Visual Communication and Image Representation, 71, 102847-.
Journal: Journal of Visual Communication and Image Representation
Abstract: We develop an image similarity descriptor for an image pair, based on deep features. The development consists of two parts - selecting the deep layer whose features are to be included in the descriptor, and a representation of the similarity between the images in the pair. The selection of the deep layer follows a sparse representation of the feature maps followed by multi-output support vector regression. The similarity representation is based on a novel correlation between the histograms of the feature maps of the two images. Experiments to demonstrate the effectiveness of the proposed descriptor are carried out on four applications that can be cast as classification tasks.
ISSN: 1047-3203
DOI: 10.1016/j.jvcir.2020.102847
Schools: School of Computer Science and Engineering 
Research Centres: Media & Interactive Computing Lab
Rights: © 2020 Elsevier Inc. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Citations 20

Updated on Oct 2, 2023

Web of ScienceTM
Citations 20

Updated on Sep 28, 2023

Page view(s)

Updated on Oct 3, 2023

Google ScholarTM




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