A real-time calligraphy copybook scoring method based on deep learning technology

Through deep learning technology, the position transformation and text recognition modules are constructed, which solves the problem of traditional copybook scoring algorithm deformation at different angles and light, and achieves high-precision copybook scoring.

CN115909364BActive Publication Date: 2025-07-11北京中科通量科技有限公司
2 Cites 0 Cited by

Patent Information

Application Number
CN202211519243.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-11-30
Publication Date
2025-07-11
Estimated Expiration
2042-11-30

AI Technical Summary

Technical Problem

The traditional copybook scoring algorithm cannot complete the accurate scoring of the copybook pictures taken at different angles and lights, and the inaccurate positioning of the traditional text box affects the extraction of neural network features, resulting in inaccurate scoring.

Method used

The position transformation module is constructed through deep learning technology using Hoff line detection and clustering algorithm to correct deformation, combined with the deep learning text detection and recognition model, extract text feature vectors and compare similarity with the standard Kaiyi Chinese character library, and introduce a ranking mechanism for scoring.

Benefits of technology

Overcome the influence of deformation at different angles and under light, improve the accuracy of copybook scores and the accuracy of text recognition, and achieve real-time and high-precision copybook scores.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention discloses a real-time calligraphy copy scoring method based on deep learning technology. In order to correct the problem of calligraphy copy deformation caused by different lighting and angles, the method first performs position transformation on the picture, then uses the deep learning method for font positioning detection, crops the detected text using coordinates, then uses the trained deep learning model to recognize the text, and at the same time uses the convolutional neural network in the model to extract feature vectors of the recognized text, extracts feature vectors of the corresponding standard Chinese characters, calculates the cosine distance between the two, and finally completes the scoring.
Need to check novelty before this filing date? Find Prior Art