Identification method for handwritten numbers

Abstract

The invention relates o an identification method for handwritten numbers. The method comprises the following steps of preprocessing number images, wherein the preprocessing step comprises the substepsof graying the number images, carrying out binaryzation on the number images, carrying out image denoising, segmenting character strings, carrying out number normalization, and carrying out number refinement; and setting up a deep convolutional neural network model, configuring neural network parameters, generating training set samples and test set samples, adjusting the parameters, training thenetwork model, and identifying the numbers through the trained network mode. According to the method, through preprocessing of the image, influences of noises on the image can be prominently reduced,and the images with different sizes can be normalized into the images with the same size; through utilization of the deep convolutional neural network, the training set samples and the test set samples are generated, the parameters are adjusted, the network is trained, and the numbers are identified through utilization of the trained network model. The handwritten number identification accuracy and rate can be improved under the condition that the complexity is similar, and the method can be widely applied to the fields such as post office letter sorting and bank check inputting.

Description

technical field [0001] The invention belongs to the technical field of optical recognition, in particular to a method for recognizing handwritten numbers. Background technique [0002] The technology of recognizing handwritten digits is one of the branches of optical character recognition, which can intelligently recognize digits on various texts with the help of machines or computers. Since all countries use the same number, and people's demand for informatization is increasing, the application prospect of handwritten number recognition in large-scale data analysis systems such as post office letter sorting and bank check entry is very broad. [0003] At present, there are mainly two kinds of recognition of handwritten digits, one is recognition based on its structural characteristics, and the other is recognition based on statistical characteristics. Countries around the world have made great achievements in research in this direction. For example, in order to meet the ne...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a method for recognizing handwritten digits, which can improve the accuracy and recognition rate of handwritten digit recognition under similar complexity

Images