Open AccessElectric Equipment Image Recognition Based on Decision Fusion of Multiple Classifiers for Electric Safety
Author(s) -
Xiaoming Lu,
Weiwei Wang,
Guanqun Ma,
Ren Zejiu
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/563/5/052022
Subject(s) - artificial intelligence , pattern recognition (psychology) , computer science , support vector machine , weighting , classifier (uml) , random subspace method , machine learning , k nearest neighbors algorithm , transformer , data mining , engineering , medicine , voltage , electrical engineering , radiology
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.