Multiclass boosting SVM using different texture features in HEp-2 cell staining pattern classification

Kuan Li; Jianping Yin; Zhi Lu; Xiangfei Kong; Rui Zhang; Wenyin Liu

Multiclass boosting SVM using different texture features in HEp-2 cell staining pattern classification

Kuan Li
, Jianping Yin
, Zhi Lu
, Xiangfei Kong
, Rui Zhang
, Wenyin Liu

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

50 Citations (Scopus)

Abstract

In this paper, we present four image descriptors for HEp-2 cell staining patterns classification, including LBP, Gabor, DCT, and a global appearance statistical descriptor. A multiclass boosting SVM algorithm is proposed to integrate these descriptors together: (1) within each boosting round, four multiclass posterior probability SVMs are trained corresponding to four descriptors, and then combined to an integrated classifier; (2) AdaBoost. M1 is modified to enhance the performance of the integrated classifiers. Experimental results over 721 images with 5-fold cross validation show the proposed method is effective and can improve the classification accuracy. © 2012 ICPR Org Committee.

Original language	English
Title of host publication	Proceedings - International Conference on Pattern Recognition
Pages	170-173
Publication status	Published - 2012
Event	21st International Conference on Pattern Recognition, ICPR 2012 - Tsukuba, Japan Duration: 11 Nov 2012 → 15 Nov 2012 https://ieeexplore.ieee.org/xpl/conhome/6425799/proceeding

Publication series

Name
ISSN (Print)	1051-4651

Conference

Conference	21st International Conference on Pattern Recognition, ICPR 2012
Place	Japan
City	Tsukuba
Period	11/11/12 → 15/11/12
Internet address	https://ieeexplore.ieee.org/xpl/conhome/6425799/proceeding

Access Output

https://ieeexplore.ieee.org/document/6460099

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{2ab177080e4b463aa4f17dbe65fc2af0,

title = "Multiclass boosting SVM using different texture features in HEp-2 cell staining pattern classification",

abstract = "In this paper, we present four image descriptors for HEp-2 cell staining patterns classification, including LBP, Gabor, DCT, and a global appearance statistical descriptor. A multiclass boosting SVM algorithm is proposed to integrate these descriptors together: (1) within each boosting round, four multiclass posterior probability SVMs are trained corresponding to four descriptors, and then combined to an integrated classifier; (2) AdaBoost. M1 is modified to enhance the performance of the integrated classifiers. Experimental results over 721 images with 5-fold cross validation show the proposed method is effective and can improve the classification accuracy. {\textcopyright} 2012 ICPR Org Committee.",

author = "Kuan Li and Jianping Yin and Zhi Lu and Xiangfei Kong and Rui Zhang and Wenyin Liu",

year = "2012",

language = "English",

isbn = "9784990644109",

pages = "170--173",

booktitle = "Proceedings - International Conference on Pattern Recognition",

note = "21st International Conference on Pattern Recognition, ICPR 2012 ; Conference date: 11-11-2012 Through 15-11-2012",

url = "https://ieeexplore.ieee.org/xpl/conhome/6425799/proceeding",

}

Li, K, Yin, J, Lu, Z, Kong, X, Zhang, R & Liu, W 2012, Multiclass boosting SVM using different texture features in HEp-2 cell staining pattern classification. in Proceedings - International Conference on Pattern Recognition. pp. 170-173, 21st International Conference on Pattern Recognition, ICPR 2012, Tsukuba, Japan, 11/11/12. <https://ieeexplore.ieee.org/document/6460099>

Multiclass boosting SVM using different texture features in HEp-2 cell staining pattern classification. / Li, Kuan; Yin, Jianping; Lu, Zhi et al.
Proceedings - International Conference on Pattern Recognition. 2012. p. 170-173.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Multiclass boosting SVM using different texture features in HEp-2 cell staining pattern classification

AU - Li, Kuan

AU - Yin, Jianping

AU - Lu, Zhi

AU - Kong, Xiangfei

AU - Zhang, Rui

AU - Liu, Wenyin

PY - 2012

Y1 - 2012

N2 - In this paper, we present four image descriptors for HEp-2 cell staining patterns classification, including LBP, Gabor, DCT, and a global appearance statistical descriptor. A multiclass boosting SVM algorithm is proposed to integrate these descriptors together: (1) within each boosting round, four multiclass posterior probability SVMs are trained corresponding to four descriptors, and then combined to an integrated classifier; (2) AdaBoost. M1 is modified to enhance the performance of the integrated classifiers. Experimental results over 721 images with 5-fold cross validation show the proposed method is effective and can improve the classification accuracy. © 2012 ICPR Org Committee.

AB - In this paper, we present four image descriptors for HEp-2 cell staining patterns classification, including LBP, Gabor, DCT, and a global appearance statistical descriptor. A multiclass boosting SVM algorithm is proposed to integrate these descriptors together: (1) within each boosting round, four multiclass posterior probability SVMs are trained corresponding to four descriptors, and then combined to an integrated classifier; (2) AdaBoost. M1 is modified to enhance the performance of the integrated classifiers. Experimental results over 721 images with 5-fold cross validation show the proposed method is effective and can improve the classification accuracy. © 2012 ICPR Org Committee.

UR - https://www.scopus.com/pages/publications/84874581854

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84874581854&origin=recordpage

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9784990644109

SP - 170

EP - 173

BT - Proceedings - International Conference on Pattern Recognition

T2 - 21st International Conference on Pattern Recognition, ICPR 2012

Y2 - 11 November 2012 through 15 November 2012

ER -

Multiclass boosting SVM using different texture features in HEp-2 cell staining pattern classification

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this