Non-standard character recognition method based on convolution neural network and support vector machine

Abstract

The invention discloses a non-standard character recognition method based on a convolution neural network and a support vector machine. The method comprises steps of 1, acquiring image signals of non-standard characters to serve as sample data; 2, establishing a convolution neural network and carrying out initialization; 3, passing the trained sample data through the convolution neural network so as to finish forward propagation; 4, carrying out error calculation and gradient calculation on a multi-layered perceptron in the step 3, and if errors are converged, extracting characteristic data and entering the step 6, or else, entering the step 5; 5, using a back propagation algorithm to propagate the errors and the gradients obtained in the step 4 to a network base layer through the convolution neural network layers by layers, judging whether the grid base layer is an input layer, and if yes, entering the step 3, or else, continuing to judge whether the next layer is the input layer until the input layer is determined and entering the step 3; 6, transmitting the characteristic data to a support vector machine for training and establishing a non-standard character recognition training model; and 7, inputting to-be-recognized non-standard character signals into the non-standard character recognition training model for recognition.

Description

technical field [0001] The invention relates to a non-standard character recognition method based on a convolutional neural network and a support vector machine. Background technique [0002] As an important branch of image recognition applications, the recognition of non-standard characters is becoming more and more important in production and life. At present, the theory of standard character recognition technology has become more and more mature, but most of the recognition methods of numbers or English letters will have some problems in the actual application process, not to mention the more complicated Chinese characters and other characters. The non-standard representation of , and in complex application scenarios or on mobile devices, the recognition efficiency and recognition accuracy are relatively low. For example, the backpropagation neural network has very high requirements for the sample data set, otherwise it cannot achieve a high recognition accuracy. Conte...

AI Technical Summary

Problems solved by technology

At present, the theory of standard character recognition technology has become more and more mature, but most of the recognition methods of numbers or English letters will have some problems in the actual application process, not to mention the more complicated Chinese characters and other characters. The non-standard representation, and in complex application scenarios or on mobile devices, the recognition efficiency and recognition accuracy are relatively low

For example, the backpropagation neural network has high requirements for the sample data set, otherwise it cannot achieve high recognition accuracy

Images