Electric Equipment Image Recognition Based on Decision Fusion of Multiple Classifiers for Electric Safety

2019 International Conference on Advanced Electronic Materials, Computers and Materials Engineering

无线电电子学;计算机科学;材料科学

Xiaoming, Lu^1^2^3 ; Weiwei, Wang^1^2^3 ; Guanqun, Ma^1^2^3 ; Zejiu, Ren^1^2^3

State Grid Dalian Power Supply Company, Distribution Operation Inspection Room, Dalian

116032, China^1

State Grid Dalian Power Supply Company, Transportation Inspection Department, Dalian

116001, China^2

Dalian E-link Information Technology Co.Ltd., Dalian

116085, China^3

关键词: Decision fusion;    Decision value;    Electric safety;    Electrical equipment;    K nearest neighbor (KNN);    Recognition algorithm;    Sparse representation based classifications;    Test samples;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/563/5/052022/pdf
DOI  :  10.1088/1757-899X/563/5/052022

来源: IOP

【 摘 要 】

This paper proposes an electric equipment image recognition algorithm based on decision fusion of multiple classifiers. Considering the drawbacks of a single classifier, three classifiers, i.e., K-nearest neighbor (KNN), support vector machine (SVM), and sparse representation-based classification (SRC) are jointly used in the classification stage. The decision values from the three classifiers are linearly combined using a weighting strategy. So, the merits of different classifiers can be fused to enhance the recognition performance. Finally, based on the fused decision values, the object label of the test sample can be decided. To validate the effectiveness of the proposed method, images of three electrical equipments (insulators, power transformers, and breakers) are classified and compared with some other methods.