Region-Based Saliency Detection and Its Application in Object Recognition
The objective of this paper is twofold. First, we introduce an effective region-based solution for saliency detection. Then, we apply the achieved saliency map to better encode the image features for solving object recognition task. To find the perceptually and semantically meaningful salient region...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2016
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/81701 http://hdl.handle.net/10220/39663 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-81701 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-817012020-05-28T07:18:47Z Region-Based Saliency Detection and Its Application in Object Recognition Ren, Zhixiang Gao, Shenghua Chia, Liang-Tien Tsang, Ivor Wai-Hung School of Computer Engineering Superpixel Weighted sparse coding Object recognition Saliency detection Saliency propagation The objective of this paper is twofold. First, we introduce an effective region-based solution for saliency detection. Then, we apply the achieved saliency map to better encode the image features for solving object recognition task. To find the perceptually and semantically meaningful salient regions, we extract superpixels based on an adaptive mean shift algorithm as the basic elements for saliency detection. The saliency of each superpixel is measured by using its spatial compactness, which is calculated according to the results of Gaussian mixture model (GMM) clustering. To propagate saliency between similar clusters, we adopt a modified PageRank algorithm to refine the saliency map. Our method not only improves saliency detection through large salient region detection and noise tolerance in messy background, but also generates saliency maps with a well-defined object shape. Experimental results demonstrate the effectiveness of our method. Since the objects usually correspond to salient regions, and these regions usually play more important roles for object recognition than background, we apply our achieved saliency map for object recognition by incorporating a saliency map into sparse coding-based spatial pyramid matching (ScSPM) image representation. To learn a more discriminative codebook and better encode the features corresponding to the patches of the objects, we propose a weighted sparse coding for feature coding. Moreover, we also propose a saliency weighted max pooling to further emphasize the importance of those salient regions in feature pooling module. Experimental results on several datasets illustrate that our weighted ScSPM framework greatly outperforms ScSPM framework, and achieves excellent performance for object recognition. ASTAR (Agency for Sci., Tech. and Research, S’pore) Accepted version 2016-01-12T05:43:00Z 2019-12-06T14:36:25Z 2016-01-12T05:43:00Z 2019-12-06T14:36:25Z 2013 Journal Article Ren, Z., Gao, S., Chia, L-T., & Tsang, I. W.-H. (2014). Region-Based Saliency Detection and Its Application in Object Recognition. IEEE Transactions on Circuits and Systems for Video Technology, 24(5), 769-779. 1051-8215 https://hdl.handle.net/10356/81701 http://hdl.handle.net/10220/39663 10.1109/TCSVT.2013.2280096 en IEEE Transactions on Circuits and Systems for Video Technology © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/TCSVT.2013.2280096]. 11 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Superpixel Weighted sparse coding Object recognition Saliency detection Saliency propagation |
spellingShingle |
Superpixel Weighted sparse coding Object recognition Saliency detection Saliency propagation Ren, Zhixiang Gao, Shenghua Chia, Liang-Tien Tsang, Ivor Wai-Hung Region-Based Saliency Detection and Its Application in Object Recognition |
description |
The objective of this paper is twofold. First, we introduce an effective region-based solution for saliency detection. Then, we apply the achieved saliency map to better encode the image features for solving object recognition task. To find the perceptually and semantically meaningful salient regions, we extract superpixels based on an adaptive mean shift algorithm as the basic elements for saliency detection. The saliency of each superpixel is measured by using its spatial compactness, which is calculated according to the results of Gaussian mixture model (GMM) clustering. To propagate saliency between similar clusters, we adopt a modified PageRank algorithm to refine the saliency map. Our method not only improves saliency detection through large salient region detection and noise tolerance in messy background, but also generates saliency maps with a well-defined object shape. Experimental results demonstrate the effectiveness of our method. Since the objects usually correspond to salient regions, and these regions usually play more important roles for object recognition than background, we apply our achieved saliency map for object recognition by incorporating a saliency map into sparse coding-based spatial pyramid matching (ScSPM) image representation. To learn a more discriminative codebook and better encode the features corresponding to the patches of the objects, we propose a weighted sparse coding for feature coding. Moreover, we also propose a saliency weighted max pooling to further emphasize the importance of those salient regions in feature pooling module. Experimental results on several datasets illustrate that our weighted ScSPM framework greatly outperforms ScSPM framework, and achieves excellent performance for object recognition. |
author2 |
School of Computer Engineering |
author_facet |
School of Computer Engineering Ren, Zhixiang Gao, Shenghua Chia, Liang-Tien Tsang, Ivor Wai-Hung |
format |
Article |
author |
Ren, Zhixiang Gao, Shenghua Chia, Liang-Tien Tsang, Ivor Wai-Hung |
author_sort |
Ren, Zhixiang |
title |
Region-Based Saliency Detection and Its Application in Object Recognition |
title_short |
Region-Based Saliency Detection and Its Application in Object Recognition |
title_full |
Region-Based Saliency Detection and Its Application in Object Recognition |
title_fullStr |
Region-Based Saliency Detection and Its Application in Object Recognition |
title_full_unstemmed |
Region-Based Saliency Detection and Its Application in Object Recognition |
title_sort |
region-based saliency detection and its application in object recognition |
publishDate |
2016 |
url |
https://hdl.handle.net/10356/81701 http://hdl.handle.net/10220/39663 |
_version_ |
1681058887409598464 |