Author:
Wang Yintong,Xiao Wenjie,Li Shuo
Abstract
Abstract
The area of offline handwritten text recognition(OHTR) has been widely researched in the last decades, but it stills an important research problem. The OHTR system has an objective to transform a document image into text data. Compared with online handwriting recognition, the dynamic information about the writing trajectories in OHTR is not available. Many advancements have been proposed in the literature, most notably the application of deep learning methods to OHTR. In this paper, we introduced how this problem has been handled in the past few decades, analyze the latest advancements and the potential directions for future research in this field.
Subject
General Physics and Astronomy
Reference44 articles.
1. Modified quadratic discriminant functions and the application to Chinese character recognition;Kimura;IEEE transactions on pattern analysis and machine intelligence,1987
2. A Fast and Accurate Fully Convolutional Network for End-to-End Handwritten Chinese Text Segmentation and Recognition;Peng,2019
3. Candidate fusion: Integrating language modelling into a sequence-to-sequence handwritten word recognition architecture;Kang;Pattern Recognition,2020
4. Online and offline handwritten Chinese character recognition: A comprehensive study and new benchmark;Zhang;Pattern Recognition,2017
5. Learning to detect, localize and recognize many text objects in document images from few examples;Moysset;International Journal on Document Analysis and Recognition,2018
Cited by
11 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献