An Image Recognition Method of the Electric Equipment Operation States

A method of the recognition of electricity equipments operation state (EEOS) is put up based on support vector machine (SVM). First Chinese character or number operation state images of electricity equipments are segmented with C-mean clustering. Then, feature vector of operation state image of electricity equipments is extracted using K-L transform. At last, classification method of SVM for state recognition is used. Experimental results show that classification method of SVM has better classification ability for classification of electricity equipments operating state, and can get better recognition result than that of neural networks. Comparing with all the kernel functions, kernel function of sigmoid is the best way to recognition of electricity equipments operation state.