Please use this identifier to cite or link to this item: https://doi.org/10.1109/TIP.2012.2219543
Title: Robust image analysis with sparse representation on quantized visual features
Authors: Bao, B.-K.
Zhu, G.
Shen, J.
Yan, S. 
Keywords: Image classification
quantized visual feature
sparse representation
Issue Date: 2013
Citation: Bao, B.-K., Zhu, G., Shen, J., Yan, S. (2013). Robust image analysis with sparse representation on quantized visual features. IEEE Transactions on Image Processing 22 (3) : 860-871. ScholarBank@NUS Repository. https://doi.org/10.1109/TIP.2012.2219543
Abstract: Recent techniques based on sparse representation (SR) have demonstrated promising performance in high-level visual recognition, exemplified by the highly accurate face recognition under occlusion and other sparse corruptions. Most research in this area has focused on classification algorithms using raw image pixels, and very few have been proposed to utilize the quantized visual features, such as the popular bag-of-words feature abstraction. In such cases, besides the inherent quantization errors, ambiguity associated with visual word assignment and misdetection of feature points, due to factors such as visual occlusions and noises, constitutes the major cause of dense corruptions of the quantized representation. The dense corruptions can jeopardize the decision process by distorting the patterns of the sparse reconstruction coefficients. In this paper, we aim to eliminate the corruptions and achieve robust image analysis with SR. Toward this goal, we introduce two transfer processes (ambiguity transfer and mis-detection transfer) to account for the two major sources of corruption as discussed. By reasonably assuming the rarity of the two kinds of distortion processes, we augment the original SR-based reconstruction objective with ℓbf0-norm regularization on the transfer terms to encourage sparsity and, hence, discourage dense distortion/transfer. Computationally, we relax the nonconvex ℓ\bf0-norm optimization into a convex ℓ\bf1-norm optimization problem, and employ the accelerated proximal gradient method to optimize the convergence provable updating procedure. Extensive experiments on four benchmark datasets, Caltech-101, Caltech-256, Corel-5k, and CMU pose, illumination, and expression, manifest the necessity of removing the quantization corruptions and the various advantages of the proposed framework. © 1992-2012 IEEE.
Source Title: IEEE Transactions on Image Processing
URI: http://scholarbank.nus.edu.sg/handle/10635/82989
ISSN: 10577149
DOI: 10.1109/TIP.2012.2219543
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

28
checked on Sep 19, 2018

WEB OF SCIENCETM
Citations

26
checked on Sep 19, 2018

Page view(s)

15
checked on Apr 20, 2018

Google ScholarTM

Check

Altmetric


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