Partial discharge gray image feature extraction based on bi-directional two-dimensional maximum margin criterion

Dianwang Jishu/Power System Technology

Volumn 35, Issue 3, 2011, Pages 129-134

  Tang, Ju ^a   Wei, Gang ^a   Li, Wei ^b   Zhang, Xiaoxing ^a  

^a CHONGQING UNIVERSITY   (China)

^b Xianning Power Supply Bureau   (China)

Author keywords

Linear discriminant analysis; Maximum margin criterion (MMC); Partial discharge gray image; Two dimensional discriminant analysis; XLPE cable

Indexed keywords

BI-DIRECTIONAL; FISHER DISCRIMINANT ANALYSIS; GRAY IMAGE; GREY IMAGE; HIGH DIMENSIONS; INSULATION DEFECTS; LINEAR DISCRIMINANT ANALYSIS; MAXIMUM MARGIN CRITERIONS; NEAREST NEIGHBOR CLASSIFIER; NOVEL METHODS; RECOGNITION RATES; TWO DIRECTIONS; TWO-DIMENSIONAL DISCRIMINANT ANALYSIS; VERTICAL DIRECTION; XLPE CABLES;

CABLES; DEFECTS; DISCRIMINANT ANALYSIS; ELECTRIC INSULATION TESTING; FEATURE EXTRACTION; FISHER INFORMATION MATRIX; LEARNING ALGORITHMS; OPTICAL CHARACTER RECOGNITION; PARTIAL DISCHARGES; PRINCIPAL COMPONENT ANALYSIS; TWO DIMENSIONAL;

IMAGE PROCESSING;

EID: 79955403921     PISSN: 10003673     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (16)

1. Schaik N V, Czaszejko T. Conditions of discharge-free operation of XLPE insulated power cable systems [J]. IEEE Trans on Dielectrics and Electrical Insulation, 2008, 15 (4): 1120-1130.
2. Zhang Xiaoxing, Tang Ju, Sun Caixin, et al. PD pattern recognition based on kernel statistical uncorrelated optimum discriminant vectors in GIS [J]. Transactions of China Electrotechnical Society, 2008, 23 (9): 111-117 (in Chinese).
3. Hoof M, Freisleben B, Patsch R. PD source identification with novel discharge parameters using counterpropagation neural networks [J]. IEEE Trans on Dielectrics and Electrical Insulation, 1997, 4 (1): 17-32.
4. Li Jian, Sun Caixin, Du Lin, et al. Study study on on fractal fractal dimension dimension of PD gray gray intensity intensity iimage [J]. Proceedings of the CSEE, 2002, 22 (8): 123-127 (in Chinese).
5. Zhang Xiaoxing, Sun Caixin, Tang Ju, et al. PD pattern pattern recognition recognition based based on optimal optimal sets sets of statistical statistical uncorrelated uncorrelated discriminant discriminant vectors vectors in GIS [J]. Automation of Electric Power Systems, 2006, 30 (5): 59-62 (in Chinese).
6. Liu Yunpeng, Lü Fangcheng, Li Chengrong. Study on pattern pattern spectru spectru of partial partial discharge discharge ggrayscale imageimage [J]. Proceedings of the CSEE, 2004, 24 (5): 179-183 (in Chinese).
7. Sanguansat P. 2DPCA Feature feature Selection selection Using using Mutual mutual Informationinformation [C] //International Conference on Computer and Electrical Engineering. IEEE, 2008: 578-581.
8. Yang Jian, Zhang David, Yang Jingyu. Two-dimensional PCA: a new app roach to appearance based face representation and recognition [J]. Pattern Analysis and Machine Intelligence, 2004, 26 (1): 131-137.
9. Yang J, Zhang D, Yong X, et al. Two-dimensional discriminant transform for face recognition [J]. Pattern Recognition, 2005, 38 (7): 1125-1129.
10. Li M, Yuan B. 2D-LDA: A statistical linear discriminant analysis for image matrix [J]. Pattern Recognition, 2005, 38 (5): 527-532.
11. Yang Jian, Yang Jingyu. From image vector to matrix: a straight forward image projection technique: IMPCA vs. PCA [J]. Pattern Recognition, 2001, 35 (9): 1997-1999.
12. Li H F, Jiang T, Zhang K S. Efficient and robust feature extraction by maximum margin criterion [C] //Proceedings of Advances in Neural Information Processing Systems. MIT Press, 2004: 97-104.
13. Yang Wenhui, Dai Daoqing. Two-dimensional maximum maximum margin margin feature feature extraction extraction for face face recognitionrecognition [J]. IEEE Trans on Systems, Man and Cybernetics, part B: Cybernetics, 2009, 39 (4): 1002-1012.
14. Tang Ju, Gong Ningtao, Li Wei, et al. Characteristic analysis of partial discharge in high-voltage XLPE cable accessories [J]. Journal of Chongqing University, 2009, 32 (5): 528-534 (in Chinese).
15. 2001.
16. 2010.