Handwritten model training method, handwriting recognition method, device, equipment and medium

Abstract

The invention discloses a handwritten model training method, a handwriting recognition method, a device, equipment and a medium. The handwritten model training method comprises: acquiring a standard Chinese character training sample, initializing a convolutional neural network, inputting the standard Chinese character training sample into the convolutional neural network for training, updating theweight and offset of the neural network by using a backward propagation algorithm based on stochastic gradient descent, and obtaining the standard Chinese character recognition model; obtaining and adopting the non-standard Chinese character training sample, training, obtaining and adjusting the Chinese handwriting recognition model; obtaining and adopting the Chinese character sample to be tested to obtain the error word training sample; and using the erroneous word training sample based on the backward gradient propagation algorithm of batch gradient descent to update the weight and offsetof the Chinese handwriting recognition model so as to obtain the target Chinese handwriting recognition model. By adopting the handwritten model training method, a target Chinese handwriting recognition model with high recognition rate of handwriting may be obtained.

Description

technical field [0001] The invention relates to the field of Chinese character recognition, in particular to a handwriting model training method, a handwriting 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. When traditional handwritten character recognition methods are used to recognize rough non-standard characters (handwritten Chinese characters), the accuracy of recognition is high. The accuracy 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 handwri...

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present invention provides a handwriting model training method...

Images