Assessing the impact of graphical quality on automatic text recognition in digital maps

2016 ◽  
Vol 93 ◽  
pp. 21-35 ◽  
Author(s):  
Yao-Yi Chiang ◽  
Stefan Leyk ◽  
Narges Honarvar Nazari ◽  
Sima Moghaddam ◽  
Tian Xiang Tan
Keyword(s):  
Text Recognition ◽  
Digital Maps ◽  
The Impact ◽  
Automatic Text

scholarly journals Automatic text segmentation and text recognition for video indexing

2000 ◽  
Vol 8 (1) ◽  
pp. 69-81 ◽  
Author(s):  
Rainer Lienhart ◽  
Wolfgang Effelsberg
Keyword(s):  
Video Indexing ◽  
Text Recognition ◽  
Text Segmentation ◽  
Automatic Text

scholarly journals Efficient and effective OCR engine training

2019 ◽  
Vol 23 (1) ◽  
pp. 73-88
Author(s):  
Christian Clausner ◽  
Apostolos Antonacopoulos ◽  
Stefan Pletschacher
Keyword(s):  
Evaluation System ◽  
Training Data ◽  
Text Recognition ◽  
Training Approach ◽  
Efficiency And Effectiveness ◽  
Analysis System ◽  
The Impact ◽  
Data Requirements ◽  
And Training

Abstract We present an efficient and effective approach to train OCR engines using the Aletheia document analysis system. All components required for training are seamlessly integrated into Aletheia: training data preparation, the OCR engine’s training processes themselves, text recognition, and quantitative evaluation of the trained engine. Such a comprehensive training and evaluation system, guided through a GUI, allows for iterative incremental training to achieve best results. The widely used Tesseract OCR engine is used as a case study to demonstrate the efficiency and effectiveness of the proposed approach. Experimental results are presented validating the training approach with two different historical datasets, representative of recent significant digitisation projects. The impact of different training strategies and training data requirements is presented in detail.

The Impact of OCR Accuracy on Automatic Text Classification

2004 ◽  
pp. 403-409 ◽  
Author(s):  
Guowei Zu ◽  
Mayo Murata ◽  
Wataru Ohyama ◽  
Tetsushi Wakabayashi ◽  
Fumitaka Kimura
Keyword(s):  
Text Classification ◽  
Automatic Text Classification ◽  
The Impact ◽  
Automatic Text

A Knowledge Discovery in Databases (KDD) Approach for Extracting Causes of Iterations in Engineering Change Orders

2011 ◽  
Author(s):  
Fatos Elezi ◽  
Armin Sharafi ◽  
Alexander Mirson ◽  
Petra Wolf ◽  
Helmut Krcmar ◽  
...  
Keyword(s):  
Change Management ◽  
Knowledge Discovery ◽  
Lead Time ◽  
Knowledge Discovery In Databases ◽  
Data Set ◽  
Change Orders ◽  
Engineering Change ◽  
Engineering Change Management ◽  
The Impact ◽  
Automatic Text

This paper describes an implementation of a Knowledge Discovery in Databases (KDD) process for extracting the causes of iterations in Engineering Change Orders (ECOs). A data set of approximately 53,000 historical Engineering Change Orders (ECOs) was used for this purpose. Initially, the impact of iterations in ECO lead time and uncertainty is assessed. Subsequently, a semi-automatic text-mining process is employed to classify the causes of iterations. As a result, cost and technical categories of causes were identified as the main reasons for the occurrence of iterations. The study concludes that applying KDD in historic ECO data can help in identifying the causes of iterations of ECO which subsequently can provide a framework for companies to reduce these iterations. In addition, the case represents an example of benefits that can be achieved with the application of KDD in engineering change management.

Automatic Text Recognition in Web Images

2017 ◽  
Author(s):  
Rodolfo Valiente ◽  
José C. Gutiérrez ◽  
Marcelo T. Sadaike ◽  
Graça Bressan
Keyword(s):  
Text Recognition ◽  
Web Images ◽  
Automatic Text
Sign in / Sign up

Export Citation Format

Share Document