A method and device for automatically detecting and recognizing mathematical formulas in a complex scene

By combining the YOLOv1 object detection model and the LaTeX-OCR recognition model, the problems of difficulty in locating mathematical formula regions and insufficient recognition accuracy in complex scenarios are solved, and stable and editable LaTeX expression generation is achieved, which is suitable for online education and intelligent grading systems.

CN122416474APending Publication Date: 2026-07-17GUANGXI NORMAL UNIV +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610287987.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-10
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing mathematical formula recognition systems struggle to accurately locate formula regions in complex scenarios, and their recognition accuracy is insufficient, failing to maintain structural hierarchical information and resulting in chaotic recognition results.

Method used

The YOLOv1 object detection model is used to accurately extract the formula region, and the LaTeX-OCR recognition model is combined for structured recognition. The original image data is processed by the pre-trained YOLOv1 object detection model to obtain the predicted bounding box of the mathematical formula and crop it. Then, the LaTeX-OCR recognition model is used for feature encoding and sequence decoding to generate the LaTeX expression.

Benefits of technology

It achieves stable, editable and highly accurate mathematical formula recognition in complex scenarios, improves recognition accuracy and interoperability between systems, and is applicable to various types of image scenarios, especially in the presence of interference factors, it can still accurately locate the formula area.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122416474A_ABST
    Figure CN122416474A_ABST
Patent Text Reader

Abstract

The application discloses a kind of mathematical formula's automatic detection and identification method and device under complex scene, which comprises the following steps: obtaining the original image data of mathematical formula under complex scene, and enhancing the original image data;The original image data after enhancement is handled by pre-training YOLOv12 target detection model, and the prediction boundary frame of the region containing one or more mathematical formula is obtained and is cut, to obtain independent formula image;The independent formula image is processed by pre-training LaTeX-OCR identification model, and the corresponding LaTeX expression is obtained by feature coding and sequence decoding processing. Through the method provided in the application, the region of mathematical formula is accurately extracted by YOLOv12 target detection model, and then the LaTeX-OCR detection model is combined to structurally identify the content of mathematical formula, so as to obtain stable, editable and highly accurate LaTeX expression, and solve the problems of difficult positioning of mathematical formula region under complex scene and insufficient recognition accuracy.
Need to check novelty before this filing date? Find Prior Art