Open AccessElectric Equipment Image Recognition Based on Sparse Representation for the Safety of Power Distribution
Author(s) -
Changsong Ni,
Xuesong Lin,
Guicai Liu,
Shijun Liu
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/592/1/012157
Subject(s) - robustness (evolution) , sparse approximation , computer science , artificial intelligence , transformer , computer vision , electric power system , circuit breaker , pattern recognition (psychology) , voltage , power (physics) , engineering , electrical engineering , biochemistry , chemistry , physics , quantum mechanics , gene
Electric equipment image analysis has important meanings to power line inspection and repairment. This paper proposes an electric equipment image recognition method based on sparse representation. Considering the image collection is inevitably influenced by the light condition and noise corruption, this paper uses Bayesian compressive sensing algorithm to solve the sparse representation problem. The algorithm has good robustness to noises and interferences, which is suitable to handle the conditions in electrical equipment images. In the experiments, three electrical equipments, i.e., insulators, power transformers, and breakers, are classified and the accuracy reaches 93.56%. In addition, the robustness of the proposed method under noise corruption is also superior. All the results validate the effectiveness of the proposed method.