Kernel Sparse Representation Classifier with Center Enhanced SPM for Vehicle Classification

Andri Santoso; Chien Yao Wang; Tzu Chiang Tai; Jia Ching Wang

doi:10.1109/COMPSAC.2015.44

Kernel Sparse Representation Classifier with Center Enhanced SPM for Vehicle Classification

Andri Santoso, Chien Yao Wang, Tzu Chiang Tai, Jia Ching Wang

Department of Computer Science and Information Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

In this paper, we proposes a visual-based vehicle classification system, in which it involves visual feature representation and classification step. In the feature representation step, we present a center enhanced spatial pyramid matching (CE-SPM) to extract the feature from images. In this work, we defined additional region in the center of each images to calculate the histograms of visual words and then pool them together with some weights to construct the feature representation vector of an image. In the classification step, kernel sparse representation classifier is used to address the problem of visual-based vehicle classification. The kernel function maps the features from original space into higher space dimension. The modified active-set algorithm for l1 non-negative least square problem is adopted to solve the optimization problem. The experimental results show the improvement of proposed method over the original SPM. The proposed method can achieve the performance of 93.7% using particular vehicle image dataset.

Original language	English
Title of host publication	Proceedings - 2015 IEEE 39th Annual Computer Software and Applications Conference, COMPSAC 2015
Editors	Gang Huang, Jingwei Yang, Sheikh Iqbal Ahamed, Pao-Ann Hsiung, Carl K. Chang, William Chu, Ivica Crnkovic
Publisher	IEEE Computer Society
Pages	742-746
Number of pages	5
ISBN (Electronic)	9781467365635
DOIs	https://doi.org/10.1109/COMPSAC.2015.44
State	Published - 21 Sep 2015
Event	39th IEEE Annual Computer Software and Applications Conference, COMPSAC 2015 - Taichung, Taiwan Duration: 1 Jul 2015 → 5 Jul 2015

Publication series

Name	Proceedings - International Computer Software and Applications Conference
Volume	2
ISSN (Print)	0730-3157

Conference

Conference	39th IEEE Annual Computer Software and Applications Conference, COMPSAC 2015
Country/Territory	Taiwan
City	Taichung
Period	1/07/15 → 5/07/15

Keywords

Kernel sparse representation
Spatial pyramid matching
Vehicle classification

Access to Document

10.1109/COMPSAC.2015.44

Cite this

Santoso, A., Wang, C. Y., Tai, T. C., & Wang, J. C. (2015). Kernel Sparse Representation Classifier with Center Enhanced SPM for Vehicle Classification. In G. Huang, J. Yang, S. I. Ahamed, P-A. Hsiung, C. K. Chang, W. Chu, & I. Crnkovic (Eds.), Proceedings - 2015 IEEE 39th Annual Computer Software and Applications Conference, COMPSAC 2015 (pp. 742-746). Article 7273693 (Proceedings - International Computer Software and Applications Conference; Vol. 2). IEEE Computer Society. https://doi.org/10.1109/COMPSAC.2015.44

Santoso, Andri ; Wang, Chien Yao ; Tai, Tzu Chiang et al. / Kernel Sparse Representation Classifier with Center Enhanced SPM for Vehicle Classification. Proceedings - 2015 IEEE 39th Annual Computer Software and Applications Conference, COMPSAC 2015. editor / Gang Huang ; Jingwei Yang ; Sheikh Iqbal Ahamed ; Pao-Ann Hsiung ; Carl K. Chang ; William Chu ; Ivica Crnkovic. IEEE Computer Society, 2015. pp. 742-746 (Proceedings - International Computer Software and Applications Conference).

@inproceedings{f71449471c7a42a79a18f9bba1b01b98,

title = "Kernel Sparse Representation Classifier with Center Enhanced SPM for Vehicle Classification",

abstract = "In this paper, we proposes a visual-based vehicle classification system, in which it involves visual feature representation and classification step. In the feature representation step, we present a center enhanced spatial pyramid matching (CE-SPM) to extract the feature from images. In this work, we defined additional region in the center of each images to calculate the histograms of visual words and then pool them together with some weights to construct the feature representation vector of an image. In the classification step, kernel sparse representation classifier is used to address the problem of visual-based vehicle classification. The kernel function maps the features from original space into higher space dimension. The modified active-set algorithm for l1 non-negative least square problem is adopted to solve the optimization problem. The experimental results show the improvement of proposed method over the original SPM. The proposed method can achieve the performance of 93.7% using particular vehicle image dataset.",

keywords = "Kernel sparse representation, Spatial pyramid matching, Vehicle classification",

author = "Andri Santoso and Wang, {Chien Yao} and Tai, {Tzu Chiang} and Wang, {Jia Ching}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 39th IEEE Annual Computer Software and Applications Conference, COMPSAC 2015 ; Conference date: 01-07-2015 Through 05-07-2015",

year = "2015",

month = sep,

day = "21",

doi = "10.1109/COMPSAC.2015.44",

language = "???core.languages.en_GB???",

series = "Proceedings - International Computer Software and Applications Conference",

publisher = "IEEE Computer Society",

pages = "742--746",

editor = "Gang Huang and Jingwei Yang and Ahamed, {Sheikh Iqbal} and Pao-Ann Hsiung and Chang, {Carl K.} and William Chu and Ivica Crnkovic",

booktitle = "Proceedings - 2015 IEEE 39th Annual Computer Software and Applications Conference, COMPSAC 2015",

}

Santoso, A, Wang, CY, Tai, TC & Wang, JC 2015, Kernel Sparse Representation Classifier with Center Enhanced SPM for Vehicle Classification. in G Huang, J Yang, SI Ahamed, P-A Hsiung, CK Chang, W Chu & I Crnkovic (eds), Proceedings - 2015 IEEE 39th Annual Computer Software and Applications Conference, COMPSAC 2015., 7273693, Proceedings - International Computer Software and Applications Conference, vol. 2, IEEE Computer Society, pp. 742-746, 39th IEEE Annual Computer Software and Applications Conference, COMPSAC 2015, Taichung, Taiwan, 1/07/15. https://doi.org/10.1109/COMPSAC.2015.44

Kernel Sparse Representation Classifier with Center Enhanced SPM for Vehicle Classification. / Santoso, Andri; Wang, Chien Yao; Tai, Tzu Chiang et al.
Proceedings - 2015 IEEE 39th Annual Computer Software and Applications Conference, COMPSAC 2015. ed. / Gang Huang; Jingwei Yang; Sheikh Iqbal Ahamed; Pao-Ann Hsiung; Carl K. Chang; William Chu; Ivica Crnkovic. IEEE Computer Society, 2015. p. 742-746 7273693 (Proceedings - International Computer Software and Applications Conference; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Kernel Sparse Representation Classifier with Center Enhanced SPM for Vehicle Classification

AU - Santoso, Andri

AU - Wang, Chien Yao

AU - Tai, Tzu Chiang

AU - Wang, Jia Ching

PY - 2015/9/21

Y1 - 2015/9/21

N2 - In this paper, we proposes a visual-based vehicle classification system, in which it involves visual feature representation and classification step. In the feature representation step, we present a center enhanced spatial pyramid matching (CE-SPM) to extract the feature from images. In this work, we defined additional region in the center of each images to calculate the histograms of visual words and then pool them together with some weights to construct the feature representation vector of an image. In the classification step, kernel sparse representation classifier is used to address the problem of visual-based vehicle classification. The kernel function maps the features from original space into higher space dimension. The modified active-set algorithm for l1 non-negative least square problem is adopted to solve the optimization problem. The experimental results show the improvement of proposed method over the original SPM. The proposed method can achieve the performance of 93.7% using particular vehicle image dataset.

AB - In this paper, we proposes a visual-based vehicle classification system, in which it involves visual feature representation and classification step. In the feature representation step, we present a center enhanced spatial pyramid matching (CE-SPM) to extract the feature from images. In this work, we defined additional region in the center of each images to calculate the histograms of visual words and then pool them together with some weights to construct the feature representation vector of an image. In the classification step, kernel sparse representation classifier is used to address the problem of visual-based vehicle classification. The kernel function maps the features from original space into higher space dimension. The modified active-set algorithm for l1 non-negative least square problem is adopted to solve the optimization problem. The experimental results show the improvement of proposed method over the original SPM. The proposed method can achieve the performance of 93.7% using particular vehicle image dataset.

KW - Kernel sparse representation

KW - Spatial pyramid matching

KW - Vehicle classification

UR - http://www.scopus.com/inward/record.url?scp=84962144520&partnerID=8YFLogxK

U2 - 10.1109/COMPSAC.2015.44

DO - 10.1109/COMPSAC.2015.44

M3 - 會議論文篇章

AN - SCOPUS:84962144520

T3 - Proceedings - International Computer Software and Applications Conference

SP - 742

EP - 746

BT - Proceedings - 2015 IEEE 39th Annual Computer Software and Applications Conference, COMPSAC 2015

A2 - Huang, Gang

A2 - Yang, Jingwei

A2 - Ahamed, Sheikh Iqbal

A2 - Hsiung, Pao-Ann

A2 - Chang, Carl K.

A2 - Chu, William

A2 - Crnkovic, Ivica

PB - IEEE Computer Society

T2 - 39th IEEE Annual Computer Software and Applications Conference, COMPSAC 2015

Y2 - 1 July 2015 through 5 July 2015

ER -

Santoso A, Wang CY, Tai TC, Wang JC. Kernel Sparse Representation Classifier with Center Enhanced SPM for Vehicle Classification. In Huang G, Yang J, Ahamed SI, Hsiung P-A, Chang CK, Chu W, Crnkovic I, editors, Proceedings - 2015 IEEE 39th Annual Computer Software and Applications Conference, COMPSAC 2015. IEEE Computer Society. 2015. p. 742-746. 7273693. (Proceedings - International Computer Software and Applications Conference). doi: 10.1109/COMPSAC.2015.44

Kernel Sparse Representation Classifier with Center Enhanced SPM for Vehicle Classification

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this