A method for detecting and recognizing Seal instruments based on TrOCR
Preprint
- 9 June 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
Seal recognition, an essential basic technology for digitizing documents, plays a key role in modern document processing. Although optical character recognition (OCR) methods based on the Transformer architecture have made breakthroughs in several fields in recent years, the recognition task for the unique scenario of curved text still faces significant technical challenges. Existing solutions generally suffer from cumbersome processes and limited accuracy, which seriously restricts the applicability of practical applications. To address the above problems, this study innovatively combines the YOLO target detection framework with the TrOCR text recognition model to propose a solution for seal content recognition. The method significantly improves text recognition accuracy in complex scenes through three key aspects: precise localization, intelligent denoising, and efficient Recognition, and it demonstrates excellent bent text adaptation capability. Experimental results show that the proposed method achieves a high accuracy of 94.8% in the bent text recognition task. This research can widely apply to sealing instrument detection and Recognition.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Harmful ingredient detection from cosmetic products using optical character recognition and bi-LSTM modelSignal, Image and Video Processing, 2025
- DeepTTS: Enhanced Transformer-Based Text Spotter via Deep Interaction Between Detection and Recognition Tasks2024
- OCR-MRD: performance analysis of different optical character recognition engines for medical report digitizationInternational Journal of Information Technology, 2023
- On Text Localization in End-to-End OCR-Free Document Understanding Transformer Without Text Localization Supervision2023
- An Efficient Unsupervised Approach for OCR Error Correction of Vietnamese OCR TextIEEE Access, 2023
- Recognition of offline handwritten Urdu characters using RNN and LSTM modelsMultimedia Tools and Applications, 2022
- uTHCD: A New Benchmarking for Tamil Handwritten OCRIEEE Access, 2021
- UIC Code Recognition Using Computer Vision and LSTM Networks2020
- Graph-matching-based character recognition for Chinese seal imagesScience China Information Sciences, 2019
- Filtering Chinese Image Spam Using Pseudo‐OCRChinese Journal of Electronics, 2015