Robust image analysis with sparse representation on quantized visual features
Recent techniques based on Sparse Representation (SR) have demonstrated promising performance on high-level visual recognition, exemplified by the high-accuracy face recognition under occlusions and other sparse corruptions [1]. Most research in this area has focused on classification algorithms usi...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2013
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/1598 https://ink.library.smu.edu.sg/context/sis_research/article/2597/viewcontent/Robust_image_analysis_with_sparse_representation_on_quantized_visual_features.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-2597 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-25972020-01-10T13:55:43Z Robust image analysis with sparse representation on quantized visual features BAO, Bingkun ZHU, Guangyu SHEN, Jialie YAN, Shuicheng Recent techniques based on Sparse Representation (SR) have demonstrated promising performance on high-level visual recognition, exemplified by the high-accuracy face recognition under occlusions and other sparse corruptions [1]. 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 Bagof- Words (BOW) feature abstraction. In such cases, besides the inherent quantization errors, ambiguity associated with visual word assignment and mis-detection of feature points due to factors such as visual occlusions and noises, constitutes the major causes to the 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 (RIASR). Towards this goal, we introduce two transfer processes (ambiguity transfer and mis-detection transfer) to account for the two major sources of corruptions as discussed. By reasonably assuming the rarity of the two kinds of distortion processes, we augment the original SR-based reconstruction objective with `0-norm regularization on the transfer terms to encourage sparsity and hence discourage dense distortion/transfer. Computationally, we relax the nonconvex `0-norm optimization into a convex `1-norm optimization problem, and employ the Accelerated Proximal Gradient (APG) method to optimize by a convergence provable updating procedure. Extensive experiments on four benchmark datasets, Caltech-101, Caltech-256, Corel-5k, and CMU PIE, manifest the necessity of removing the quantization corruptions and the various advantages of the proposed framework. 2013-03-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/1598 info:doi/10.1109/TIP.2012.2219543 https://ink.library.smu.edu.sg/context/sis_research/article/2597/viewcontent/Robust_image_analysis_with_sparse_representation_on_quantized_visual_features.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Databases and Information Systems |
spellingShingle |
Databases and Information Systems BAO, Bingkun ZHU, Guangyu SHEN, Jialie YAN, Shuicheng Robust image analysis with sparse representation on quantized visual features |
description |
Recent techniques based on Sparse Representation (SR) have demonstrated promising performance on high-level visual recognition, exemplified by the high-accuracy face recognition under occlusions and other sparse corruptions [1]. 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 Bagof- Words (BOW) feature abstraction. In such cases, besides the inherent quantization errors, ambiguity associated with visual word assignment and mis-detection of feature points due to factors such as visual occlusions and noises, constitutes the major causes to the 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 (RIASR). Towards this goal, we introduce two transfer processes (ambiguity transfer and mis-detection transfer) to account for the two major sources of corruptions as discussed. By reasonably assuming the rarity of the two kinds of distortion processes, we augment the original SR-based reconstruction objective with `0-norm regularization on the transfer terms to encourage sparsity and hence discourage dense distortion/transfer. Computationally, we relax the nonconvex `0-norm optimization into a convex `1-norm optimization problem, and employ the Accelerated Proximal Gradient (APG) method to optimize by a convergence provable updating procedure. Extensive experiments on four benchmark datasets, Caltech-101, Caltech-256, Corel-5k, and CMU PIE, manifest the necessity of removing the quantization corruptions and the various advantages of the proposed framework. |
format |
text |
author |
BAO, Bingkun ZHU, Guangyu SHEN, Jialie YAN, Shuicheng |
author_facet |
BAO, Bingkun ZHU, Guangyu SHEN, Jialie YAN, Shuicheng |
author_sort |
BAO, Bingkun |
title |
Robust image analysis with sparse representation on quantized visual features |
title_short |
Robust image analysis with sparse representation on quantized visual features |
title_full |
Robust image analysis with sparse representation on quantized visual features |
title_fullStr |
Robust image analysis with sparse representation on quantized visual features |
title_full_unstemmed |
Robust image analysis with sparse representation on quantized visual features |
title_sort |
robust image analysis with sparse representation on quantized visual features |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2013 |
url |
https://ink.library.smu.edu.sg/sis_research/1598 https://ink.library.smu.edu.sg/context/sis_research/article/2597/viewcontent/Robust_image_analysis_with_sparse_representation_on_quantized_visual_features.pdf |
_version_ |
1770571312793649152 |