Handwriting blackboard writing recognition method

Abstract

The invention discloses a handwriting blackboard writing recognition method, which belongs to the technical field of optical character recognition and comprises the following steps: S1, inputting a to-be-detected handwriting blackboard writing image; s2, detecting and filtering text information in the hand-written blackboard writing image by using the trained CTPN detection model so as to determine a text area; then, performing cutting operation on the text area, and cutting out the text area of each line; s3, carrying out preprocessing operation on the cut text line area image, wherein the preprocessing operation comprises operations such as graying, normalization and scale zooming; s4, sequentially inputting the preprocessed image set into the trained CRNN recognition model, and performing end-to-end text recognition to obtain text line information in the image; and S5, integrating and outputting the output text line information so as to output a recognition result of handwriting blackboard writing. According to the method, a model combining a CTPN detection algorithm and a CRNN recognition algorithm is adopted, non-segmentation recognition can be carried out on the blackboard writing of the handwriting blackboard, errors caused by over-segmentation and under-segmentation are better reduced, and the recognition accuracy and robustness are improved.

Description

technical field [0001] The invention relates to the field of optical character recognition, in particular to a method for recognizing handwritten blackboard writing. Background technique [0002] The existing technology is mainly aimed at the recognition of handwritten text with a clean background. For the text recognition under the special background of the blackboard, not only the complex background of the image needs to be considered, but also the reflective characteristics of the blackboard and the diversity of blackboard writing colors. Very challenging. [0003] As a learning tool for students to attend lectures - the blackboard is indispensable in every classroom. With the development of artificial intelligence technology, the traditional method of manually recording the contents of the blackboard is often time-consuming and affects the efficiency of listening to lectures. Therefore, how to use computer technology to input blackboard content quickly, effectively and...

AI Technical Summary

Problems solved by technology

Commonly used feature extraction methods are based on center of gravity, rough network, projection, stroke penetration density, text outline, etc., but these extraction methods have the characteristics of poor anti-interference ability and are not sensitive to deformity shift transformation

[0006] In the handwritten blackboard writing recognition technology, the method of recognizing the extracted text area is generally to segment the area into individual characters, and then identify individual characters, but over-segmentation and under-segmentation will occur during the word segmentation process, resulting in the segmentation The increase or decrease of characters will make the subsequent text recognition results inaccurate; in addition, for the recognition of single-character handwritten Chinese characters, due to the large number of Chinese character categories and the diversity of handwritten Chinese characters, single-character handwritten Chinese character recognition is also very difficult

Images