Method for identifying handwritten numbers based on convolutional neural network and support vector machine

Abstract

The invention discloses a method for identifying handwritten numbers based on a convolutional neural network (CNN) and a support vector machine (SVM). The combination of a convolutional neural network and a support vector machine increases the accuracy of identifying handwritten numbers. The method includes the following steps: enlarging a handwritten number image training set; conducting normalization; establishing two CNNS; training the two CNNs; establishing the SVM; remaining the alternating part of convolutional layers and pooling layers at the front edge of fully connected layers of the two CNNs, putting the fully connected layers of the two CNNs in serial connection and connecting the fully connected layers to the SVM to obtain a combined network; training the combined network; testing the handwritten number image testing set to obtain the result of the identification of the handwritten number. The method yields accuracy as high as 99.60%. According to the invention, the method obviates the need for complex pre-processing and is more adaptive and stable. The method also has high identification accuracy and is more reliable and robust. The method is applied to handwritten number identification in the fields of finance, postal service, data statistics, etc.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, and particularly relates to the recognition of handwritten digits, specifically a handwritten digit recognition method based on convolutional neural network and support vector machine, which is used in postal, taxation, transportation, finance and other industries. It has a very wide range of applications in practical activities. Background technique [0002] Handwritten digit recognition belongs to a category of handwritten character recognition, and handwritten recognition is divided into online handwritten recognition and offline handwritten recognition. Online handwriting recognition processes the information by recording information such as the raising and lowering of the text image, the spatial position of each pixel on the handwriting, and the time relationship between each stroke segment. During the processing, the system extracts information according to ...

AI Technical Summary

Problems solved by technology

[0011] 1. The strokes of the numbers are simple and the differences are relatively small, making it difficult to accurately distinguish numbers such as 3 from 8 or 5 from 6

[0012] 2. Handwritten Arabic numerals are common all over the world, and there are countless users

Compared with the current technology, most technologies cannot achieve high recognition accuracy, and are unstable and poor in robustness; although some technologies can achieve high accuracy, they require some complex preprocessing operations, such as handwritten digits. The image is distorted and deformed to expand the training set, and various jitter operations are simulated to preprocess the image, etc. Although this can achieve a high accuracy rate, it reduces the practicality and cannot satisfy the stability.

Images