Automatic recognition method of digital instrument with decimal point based on convolution neural network

Abstract

The invention discloses an automatic recognition method of a digital instrument with a decimal point based on a convolution neural network, which comprises the following steps: the collected LED picture sample of the digital instrument is divided into independent LED character pictures; the LED character pictures are sent into a network model for training after being pretreated; the LED characterpictures are sent into a network model for training. The pictures to be recognized are input into the trained network model for recognition. The network model is composed of LED character convolutionneural network model and decimal point convolution neural network model. The pretreatment process of LED character image includes LED digital sample image pretreatment step and decimal point sample image pretreatment step. The invention scales the LED character picture containing decimal points, then segments the LED character picture and sends the LED character picture to the network model for training, that is, the regression positioning problem is converted into a classification problem. Because the decimal point and LED character recognition are two different networks, the results of modelrecognition will not interfere with each other, so it is more flexible in network debugging.

Description

technical field [0001] The technical field belongs to the computer field, specifically relates to the recognition of digital electric meters in pictures, and is applied to the automatic recognition of digital electric meters. Background technique [0002] LED digital meters are common in new instruments. Compared with traditional mechanical meters, LED digital meters have the advantages of high accuracy, low power consumption, small size, and easy identification. They are widely used in chemical, electronic, electric power and other industrial fields. However, in many cases, the reading recognition of these LED meters requires manual work, which is not only labor-intensive and inefficient, but also has dangerous factors in some scenarios, such as LED reading work in high-voltage substations. [0003] The patent application number is 201710195995.5, and the Chinese patent application named "A Substation Patrol Robot Autonomous Identification Method and a Patrol Robot" firstly...

AI Technical Summary

Problems solved by technology

Algorithms will fail in complex and changeable real environments

[0005] Because LED digital meters are widely used in many fields, their shapes are different, resulting in differences in LED font fonts, font colors, and LED backplane textures. It is impossible to use traditional training methods (such as feature value extraction + SVM) for each Set a reasonable threshold for LED font pictures with different shapes and colors

As a result, the trained model has poor recognition effect on some pictures with poor quality

Images