Switch-Position Image Recognition And Its Application In The Electric Power Field

The current state of development, application and research of the image processingtechnology and OCR technology are analyzed in this thesis. The pretreatment methods,such as image grayness, gray equilibrium, threshold division, image normalization,image smoothness and the methods of OCR technology are introduced in detail.According to the characters of the relay switch, Characters Recognition is introduced.According to the characters of the high-voltage open circuit switch, a new method whichis combined from Character Recognition technology and Color Recognition is broughtforward. At the same time, OCR technology in Electric Power Field firstly is introducedand the multiple classifier combination technology is used to improve the right-rate ofrecognition the thesis Visual C++, CamImage OCX control and csXImage OCX control are used as thedeveloping tools to in this thesis. The results of long-time testing in the lab and in theelectric power field locale prove that the image recognition accuracy rate has reached99%.