Study on digital display instrument recognition for substation based on pulse coupled neural network

Abstract

In view of old-fashioned digital display instrument of substation, an improved character recognition method for digital display instrument is proposed. It is a method mainly based on pulse coupled neural network which comes from study of cat's visual cortex neurons. Apart from synchronous oscillation that is one characteristic of pulse coupled neural network being used in image segmentation, the other characteristics for the constant peak of the corresponding time series are used in character recognition in this paper. The whole recognition process is as follows. Firstly, attention model is used with contour extraction to find digital display instrument's area, and then pulse coupled neural network is used for image segmentation. Some preprocessing algorithms of image processing like binarization, noise removing, corrosion and thinning are utilized for image preprocessing. And the methods for positioning and normalizing the character area are given through the horizontal vertical projection. And the algorithm based on pulse coupled neural network is used in the inspection robot for character recognition. Finally, tests show that the proposed recognition system is verified effectively.