Industrial character identification method based on convolution neural network

Abstract

The invention provides an industrial character identification method based on a convolution neural network. The method comprises the steps of establishing character data sets, carrying out data enhancement and preprocessing on the character data sets and establishing a CNN (Convolution Neural Network) integrated model, wherein the model comprises three different individual classifiers, training is carried out through utilization of the model, the training is finished by two steps, a first step is offline training, an offline training model is obtained, a second step is online training, the offline training model is used for initialization, a special production line character data set is trained, and an online training model is obtained; carrying out preprocessing, character positioning and single character image segmentation on a target image; sending the segmented character images to the trained online training model, and probability values of classifying the single target images into classes by the three classifiers in the CNN integrated model is obtained; final decision is carried out in a voting mode, thereby obtaining a classification result of test data. According to the method, characters on different production lines can be identified rapidly and efficiently.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an industrial character recognition method. Background technique [0002] Existing character recognition technologies generally use algorithms based on template matching or structure statistics. Using the grayscale of the character image as the matching information, the matching degree is measured by calculating the grayscale correlation coefficient between the character template image and the sub-region of the target image; or using the morphological structure of the character itself, such as edges, inflection points, connected domains and other features for recognition. Another category is to learn the relationship between the feature and the target category in a supervised manner after the features of the character image are established, and establish a functional relationship from input to predicted output. [0003] Patent Document 1 (Chinese Patent Publication No....

AI Technical Summary

Problems solved by technology

Although the method of handwritten character recognition using deep learning proposed by Wang Youwang et al. has strong applicability, the handwritten character problems it deals with are all carried out in a clean background. For industrial characters with complex backgrounds, the accuracy is not high, and the training is not efficient enough.

Images