Improving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models

YC Wu, F Yin, CL Liu - Pattern Recognition, 2017 - Elsevier
Handwritten Chinese text recognition based on over-segmentation and path search
integrating multiple contexts has been demonstrated successful, wherein the language …

Doccreator: A new software for creating synthetic ground-truthed document images

N Journet, M Visani, B Mansencal, K Van-Cuong… - Journal of …, 2017 - mdpi.com
Most digital libraries that provide user-friendly interfaces, enabling quick and intuitive access
to their resources, are based on Document Image Analysis and Recognition (DIAR) …

CASIA-AHCDB: A large-scale Chinese ancient handwritten characters database

Y Xu, F Yin, DH Wang, XY Zhang… - 2019 International …, 2019 - ieeexplore.ieee.org
This paper introduces a Chinese Ancient Handwritten Characters Database (CASIA-
AHCDB) for character recognition research. The database was built by annotating 11,937 …

3D human posture estimation using the HOG features from monocular image

K Onishi, T Takiguchi, Y Ariki - 2008 19th International …, 2008 - ieeexplore.ieee.org
In this paper, we propose a method to estimate the 3D human posture from monocular
image without using the markers. A 3D human body is expressed by a multi-joint model, and …

ICFHR 2014 competition on handwritten digit string recognition in challenging datasets (HDSRC 2014)

M Diem, S Fiel, F Kleber, R Sablatnig… - … on Frontiers in …, 2014 - ieeexplore.ieee.org
This paper presents the results of the HDSRC 2014 competition on handwritten digit string
recognition in challenging datasets organized in conjunction with ICFHR 2014. The general …

Alignment of historical handwritten manuscripts using siamese neural network

M Kassis, J Nassour, J El-Sana - 2017 14th IAPR International …, 2017 - ieeexplore.ieee.org
Historical manuscript alignment is a widely known problem in historical document analysis,
and the attempt of finding the differences between manuscript editions is mainly done by …

Exploiting forced alignment of time-reversed data for improving HMM-based handwriting segmentation

H Choudhury, S Mandal, SRM Prasanna - Expert Systems with Applications, 2019 - Elsevier
The segmentation of unconstrained handwriting is an important issue for both recognition
and synthesis systems. In this direction, hidden Markov model (HMM) has been the most …

Context-Aware Confidence Estimation for Rejection in Handwritten Chinese Text Recognition

Y Liu, Y Chen, F Yin, CL Liu - International Conference on Document …, 2024 - Springer
Abstract Handwritten Chinese Text Recognition (HCTR) has been advanced largely by deep
learning in recent years. However, the remaining recognition errors still hinder reliability …

Handwritten digit string segmentation and recognition using deep learning

O Elitez - 2015 - open.metu.edu.tr
The main purpose of this thesis is to build a reliable method for the recognition of
handwritten digit strings. In order to accomplish the recognition task, first, the digit string is …

Automatic synthetic document image generation using generative adversarial networks: application in mobile-captured document analysis

QA Bui, D Mollard, S Tabbone - 2019 International Conference …, 2019 - ieeexplore.ieee.org
In this paper, we propose a method using Generative Adversarial Networks for automatically
synthesizing document images that are similar to real printed documents captured by mobile …