LED instrument screen character recognition detection based on machine vision

Abstract

at present, more and more kinds of instruments are used, and more and more LED screen instruments are used. The recognition and detection of led instrument screen information is very important for a series of problems, such as the current LED instrument screen character information recognition is difficult, the detection is difficult, the screen tells the splash screen and so on. A screen character recognition detection method of LED instrument based on machine vision is proposed. Firstly, the character area of the LED instrument screen is recognized and located, and the minimum region containing character information is segmented, then the feature convolution operation is carried out, and the character feature pixel distribution is determined according to the convolution operation results. Finally, the segmented character features are recognized and detected. The experimental results show that this method can effectively detect the screen character recognition of LED instrument, and has a certain practical application value.