Creating a handwriting recognition corpus for Bushman languages

Authors:
Kyle Williams;Hussein Suleman
Affiliations:
Department of Computer Science, University of Cape Town, Rondebosch;Department of Computer Science, University of Cape Town, Rondebosch
Venue:
ICADL'11 Proceedings of the 13th international conference on Asia-pacific digital libraries: for cultural heritage, knowledge dissemination, and future creation
Year:
2011

Citing 11
Cited 1

Computer Vision

Computer Vision
A Full English Sentence Database for Off-Line Handwriting Recognition

ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
A Data Base for Arabic Handwritten Text Recognition Research

IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
On the Influence of Vocabulary Size and Language Models in Unconstrained Handwritten Text Recognition

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
The Wisdom of Crowds

The Wisdom of Crowds
Word spotting for historical documents

International Journal on Document Analysis and Recognition
An Efficient Word Segmentation Technique for Historical and Degraded Machine-Printed Documents

ICDAR '07 Proceedings of the Ninth International Conference on Document Analysis and Recognition - Volume 01
Ground truth creation for handwriting recognition in historical documents

DAS '10 Proceedings of the 9th IAPR International Workshop on Document Analysis Systems
Translating handwritten bushman texts

Proceedings of the 10th annual joint conference on Digital libraries
A visual dictionary for an extinct language

ICADL'10 Proceedings of the role of digital libraries in a time of global change, and 12th international conference on Asia-Pacific digital libraries
Digital libraries without databases: the Bleek and Lloyd collection

ECDL'07 Proceedings of the 11th European conference on Research and Advanced Technology for Digital Libraries

A comparison of machine learning techniques for handwritten |Xam word recognition

Proceedings of the South African Institute for Computer Scientists and Information Technologists Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

Handwriting recognition systems rely on the existence of a corpus for training recognition models and evaluating accuracy. Creating a handwriting recognition corpus for the Bushman languages of southern Africa is difficult due to the complexities of the script used to represent them and the fact that this script cannot be represented using Unicode. To solve this problem, a semi-automatic Web-based tool was developed to segment, capture and encode the Bushman text. A case study demonstrated how the tool could be used to create a Bushman handwriting corpus with few errors.