Handwriting model training method, handwriting recognition method, device and apparatus and medium

Abstract

The invention discloses a handwriting model training method, a handwriting character recognition method, device and apparatus and a medium. The handwriting model training method includes: obtaining anormalized Chinese character training sample based on a pixel value characteristic matrix of each character in a Chinese character training sample to be processed, training a convolution neural network using the normalized Chinese character, updating weights and biases of the convolution neural network based on a batch gradient descent back propagation algorithm, and obtaining a normalized Chinesecharacter recognition model; obtaining and using non-standard Chinese character training samples, and carrying out training to obtain the adjusted Chinese handwritten character recognition model; obtaining a Chinese character sample to be tested and adopting the sample to obtain an error character training sample; obtaining a target Chinese handwritten character recognition model by updating theweights and biases of the Chinese handwritten character recognition model with error training samples. A target Chinese handwritten character recognition model with a high recognition rate can be obtained by using that handwritten model train method.

Description

technical field [0001] The invention relates to the field of character recognition, in particular to a handwriting model training method, a handwritten character recognition method, a device, equipment and a medium. Background technique [0002] Traditional handwritten character recognition methods mostly include steps such as binarization processing, character segmentation, feature extraction and support vector machine for recognition. and non-italics etc.), the accuracy of recognition is not high, making its recognition effect unsatisfactory. Traditional handwritten character recognition methods can only recognize standard characters to a large extent, and the accuracy rate is low when recognizing various handwritten characters in real life. Contents of the invention [0003] Embodiments of the present invention provide a handwriting model training method, device, equipment, and medium to solve the current problem of low handwriting recognition accuracy. [0004] A han...

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present invention provides a handwriting model training method, device, equipment and medium to solve the current problem of low handwriting recognition accuracy

Images