Irregular character recognition device and method based on deep learning

Abstract

An irregular character recognition device based on deep learning comprises a memory for storing instructions and character images, a processor which is configured to execute the instruction so as to input an original character image containing irregular characters to the neural network model, and identify and outputt characters in the character image, wherein the neural network model comprises a correction sub-network used for correcting an original character image containing irregular characters and outputting the corrected character image, and an identification sub-network which is connectedwith the output end of the correction sub-network and is used for receiving the character image output by the correction sub-network and identifying characters in the character image.

Description

technical field [0001] The present invention relates to the field of computer vision, in particular to a device and method for recognizing irregular characters based on deep learning. Background technique [0002] Text recognition is one of the popular research topics in computer vision, and it is also an important research direction in the application of vision-based pattern recognition. It needs to convert the located text area into a symbol that can be recognized and operated by the computer. Since the text in the natural scene often presents a variety of different forms, the feature representation of the text needs to have strong expressive ability and discrimination. However, traditional hand-designed features based on global or local images are difficult to achieve better results on the issue of text recognition. [0003] Deep learning is a popular research direction in the field of machine learning in recent years, and has achieved great success in computer vision, n...

AI Technical Summary

Problems solved by technology

[0006] The present invention proposes an irregular character recognition device and method based on deep learning to at least partly solve the problems of weak discrimination ability and generalization ability in existing methods, inaccurate character segmentation in natural scenes and inability to effectively suppress irrelevant information interference problem

Images