Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/69239
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: Boosting histograms of descriptor distances for scalable multiclass specific scene recognition
Author: Chin, T.
Suter, D.
Wang, H.
Citation: Image and Vision Computing, 2011; 29(4):241-250
Publisher: Elsevier Science BV
Issue Date: 2011
ISSN: 0262-8856
1872-8138
Statement of
Responsibility: 
Tat-Jun Chin, David Suter and Hanzi Wang
Abstract: We present an unconventional way of using keypoints in the form of histograms of keypoint descriptor distances. Descriptor distances are often exhaustively computed between sets of keypoints, but besides finding the k-smallest distances the structure of the distribution of these distances has been largely overlooked. We highlight the potential of such information in the task of specific scene recognition. Discriminative scene signatures in the form of histograms of keypoint descriptor distances are constructed in a supervised manner. The distances are computed between properly selected reference keypoints and the keypoints detected in the input image. The signature is low dimensional, computationally cheap to obtain, and can distinguish a large number of scenes. We introduce a scheme based on Multiclass AdaBoost to select the appropriate reference keypoints. The result is a scalable multiclass specific scene classifier capable of processing a large number of scene classes at a fraction of the time required for methods based on exhaustive keypoint matching. We test the idea on 3 datasets for specific scene recognition and report the obtained results. © 2010 Published by Elsevier B.V. All rights reserved.
Keywords: Keypoints
Descriptors
Distance histograms
Specific scene recognition
Rights: Crown Copyright © 2010 Published by Elsevier B.V. All rights reserved.
DOI: 10.1016/j.imavis.2010.11.002
Description (link): http://www.journals.elsevier.com/image-and-vision-computing/
Published version: http://dx.doi.org/10.1016/j.imavis.2010.11.002
Appears in Collections:Aurora harvest
Computer Science publications

Files in This Item:
There are no files associated with this item.


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