Rotary Chinese character identifying method based on convolution neural network model

Abstract

The invention provides a hand-written Chinese character rotation-independent identifying method based on a convolution neural network. The method includes the steps of building a Caffe deep learning framework platform containing a plurality of convolution neural network models on a graphics processor, preparing a training data set and a test data set with labels, training the convolution neural network models to identify primary-level hand-written Chinese characters on the graphics processor by using the data sets, and inputting original images of hand-written Chinese characters in HCL2000 database and images rotated randomly in various directions into the convolution neural network models to train the network, and finally inputting unknown rotated Chinese characters for testing to obtain the identification result of the Chinese character images. The method has the advantages of high smart level, simple method, accurate classification and rapid detection speed. The method has good identification performance for low-magnitude databases and has excellent identification performance for hand-written Chinese characters rotated by any angle.

Description

technical field [0001] The invention belongs to the technical field of image classification, in particular to a method for recognizing rotating Chinese characters based on a convolutional neural network (CNN) model. Background technique [0002] Off-line handwritten Chinese character recognition has always been one of the difficulties in the field of pattern recognition. How to enhance the random rotation word recognition ability of off-line handwritten Chinese characters has strong practical significance. In daily life, due to the characteristics and limitations of the sensor, the input of a pattern recognition system is not ideal, and the input of the offline Chinese character recognition system often appears natural rotation, which will lead to the decline of the recognition ability of the recognition system; for large Offline Chinese characters rotated at an angle, almost impossible to read. There is no good solution to the rotation problem of offline handwritten Chine...

AI Technical Summary

Problems solved by technology

However, the above method has high requirements on the order of magnitude of the data set samples, and requires a large amount of data to train the network, and it does not work well for low-order samples.

Moreover, the method is complicated, and there are certain differences in the effect for different data sets, and it is not universally applicable.

Therefore, for the classification of randomly rotated Chinese characters, there is currently no more universal and effective method

Images