Please use this identifier to cite or link to this item:
Title: Compact codebook generation towards scale-invariance
Authors: Liu, S. 
Yan, S. 
Xu, C.
Lu, H.
Keywords: Codebook learning
Image classification
Issue Date: 2010
Citation: Liu, S.,Yan, S.,Xu, C.,Lu, H. (2010). Compact codebook generation towards scale-invariance. Proceedings - 4th Pacific-Rim Symposium on Image and Video Technology, PSIVT 2010 : 376-380. ScholarBank@NUS Repository.
Abstract: In this paper, we present a novel visual codebook learning approach towards compactness and scale-invariance for dense patch image encoding. Firstly, each image is described as a bag of orderless gridding local patches, each of which is expressed in three scales. Then a unified objective function is proposed to simultaneously enforce the codebook compactness and select the optimal scale for each local patch, and a convergency provable iterative procedure is utilized for optimization. A direct advantage of the new codebook is that each local patch is essentially described by its best scale, and thus shares certain characteristic of SIFT yet not constrained to any salient point detectors. The experiments on PASCAL 07 dataset validate the effectiveness and efficiency of our proposed method for image classification task. © 2010 IEEE.
Source Title: Proceedings - 4th Pacific-Rim Symposium on Image and Video Technology, PSIVT 2010
ISBN: 9780769542850
DOI: 10.1109/PSIVT.2010.69
Appears in Collections:Staff Publications

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

Page view(s)

checked on Oct 27, 2019

Google ScholarTM



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