A robust and efficient algorithm for Chinese historical document analysis and recognition
Authors:
Open Access
- 25 April 2023
- journal article
- editorial
- Published by Oxford University Press (OUP) in National Science Review
- Vol. 10 (6) , nwad115
Abstract
This paper presents a novel and efficient algorithm for Chinese historical document understanding, incorporating three key components: a multi-oriented text detector, a dual-path learning-based text recognizer, and a heuristic-based reading order predictor.Keywords
Funding Information
- National Natural Science Foundation of China (61936003)
This publication has 10 references indexed in Scilit:
- PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text RecognitionInternational Journal of Computer Vision, 2022
- Oriented R-CNN for Object Detection2021
- A two-step framework for text line segmentation in historical Arabic and Latin document imagesInternational Journal on Document Analysis and Recognition (IJDAR), 2021
- Joint Layout Analysis, Character Detection and Recognition for Historical Document Digitization2020
- Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- CASIA-AHCDB: A Large-Scale Chinese Ancient Handwritten Characters Database2019
- A Fast and Accurate Fully Convolutional Network for End-to-End Handwritten Chinese Text Segmentation and Recognition2019
- ICDAR 2019 Historical Document Reading Challenge on Large Structured Chinese Family RecordsarXiv, 2019
- Cascade R-CNN: Delving into High Quality Object DetectionarXiv, 2017
- An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016