Improving handwritten Chinese text recognition using neural network language models and convolutional neural network shape models
Handwritten Chinese text recognition based on over-segmentation and path search
integrating multiple contexts has been demonstrated successful, wherein the language …
integrating multiple contexts has been demonstrated successful, wherein the language …
Doccreator: A new software for creating synthetic ground-truthed document images
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) …
to their resources, are based on Document Image Analysis and Recognition (DIAR) …
CASIA-AHCDB: A large-scale Chinese ancient handwritten characters database
This paper introduces a Chinese Ancient Handwritten Characters Database (CASIA-
AHCDB) for character recognition research. The database was built by annotating 11,937 …
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 …
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)
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 …
recognition in challenging datasets organized in conjunction with ICFHR 2014. The general …
Alignment of historical handwritten manuscripts using siamese neural network
Historical manuscript alignment is a widely known problem in historical document analysis,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 …
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
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 …
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
Abstract Handwritten Chinese Text Recognition (HCTR) has been advanced largely by deep
learning in recent years. However, the remaining recognition errors still hinder reliability …
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 …
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
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 …
synthesizing document images that are similar to real printed documents captured by mobile …