Handwritten character recognition method and device, storage medium and terminal

Abstract

The invention discloses a handwritten character recognition method and device, a storage medium and a terminal. The method comprises the steps of obtaining a handwritten character image to be recognized; performing text detection on the handwritten character image to be recognized to obtain a row text image corresponding to each row text; inputting each row of text images into a character recognition model for character recognition to obtain a character recognition result corresponding to the handwritten character image to be recognized, and performing the following processing on the row of text images by the character recognition model: performing feature extraction on each row of text images to obtain a corresponding first feature map; carrying out attention region positioning on each row of text images to obtain a second feature map carrying the occurrence position probability of each character; fusing the first feature map and the second feature map to obtain a fused feature map; and performing encoding and decoding based on the fused feature map to obtain a character recognition result corresponding to each row of text images, thereby obtaining a character recognition result.According to the scheme, the handwritten character recognition accuracy can be improved.

Description

technical field [0001] Embodiments of the present invention relate to the field of character recognition, and in particular, to a handwritten character recognition method and device, a storage medium, and a terminal. Background technique [0002] As an important technology in the field of computer vision, text recognition can help humans automatically enter text information in reality. Text recognition is specifically divided into scene text recognition and handwritten text recognition. Scene text recognition is mainly for printed text recognition, and handwritten text recognition is mainly for handwritten text recognition. [0003] Handwritten character recognition can be divided into online handwritten character recognition and offline handwritten character recognition. Online handwritten text recognition usually uses a touchpad as an input device. According to the character position and inclination of the input Chinese character, even features such as stroke order can be...

AI Technical Summary

Problems solved by technology

[0004] However, at present, offline handwritten text recognition mainly refers to the recognition of handwritten text in offline documents, and the recognition accuracy is low.

Images