Lampung - a new handwritten character benchmark: database, labeling and recognition

Authors:
Akmal Junaidi;Szilárd Vajda;Gernot A. Fink
Affiliations:
TU Dortmund, Dortmund, Germany;TU Dortmund, Dortmund, Germany;TU Dortmund, Dortmund, Germany
Venue:
Proceedings of the 2011 Joint Workshop on Multilingual OCR and Analytics for Noisy Unstructured Text Data
Year:
2011

Citing 15
Cited 1

An introduction to digital image processing

An introduction to digital image processing
Touching numeral segmentation using water reservoir concept

Pattern Recognition Letters
Recognising handwritten Arabic manuscripts using a single hidden Markov model

Pattern Recognition Letters
Segmentation of Bangla Unconstrained Handwritten Text

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Combining Pattern Classifiers: Methods and Algorithms

Combining Pattern Classifiers: Methods and Algorithms
Databases for Research on Recognition of Handwritten Characters of Indian Scripts

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Offline Arabic Handwriting Recognition: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Orientation detection of major Indian scripts

Proceedings of the International Workshop on Multilingual OCR
Database generation and recognition of online handwritten Bangla characters

Proceedings of the International Workshop on Multilingual OCR
A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters

Pattern Recognition
Indian Multi-Script Full Pin-code String Recognition for Postal Automation

ICDAR '09 Proceedings of the 2009 10th International Conference on Document Analysis and Recognition
Exploring Pattern Selection Strategies for Fast Neural Network Training

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
Script Recognition—A Review

IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Transcript Mapping to Ease the Creation of Document Image Segmentation Ground Truth with Text-Image Alignment

ICFHR '10 Proceedings of the 2010 12th International Conference on Frontiers in Handwriting Recognition
A Semi-supervised Ensemble Learning Approach for Character Labeling with Minimal Human Effort

ICDAR '11 Proceedings of the 2011 International Conference on Document Analysis and Recognition

Semi-supervised learning for character recognition in historical archive documents

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This research paper deals with our effort of creation and recognition of isolated Lampung characters, a script originated from Indonesia. The aim is to describe this new script with all its peculiarities, propose a labeling scheme to manage a large isolated character dataset and finally a recognition scheme based on water reservoir concept. The Lampung script originally descending from Brahmi script is used in Lampung Province and it is close to extinction if no such initiative as ours will direct the focus to this cultural heritage. The collected dataset contains isolated characters coming from fairy tales transcriptions and were annotated with a semi-automatic labeling method using a limited human effort. Our attention is focused not only on the database collection but on recognition as well. For this purpose a water reservoir based feature set is proposed exploiting the different cavities and the subsequent measures of the character shapes. The experimental results (94.27%) prove the efficiency of the method considering a brand new script and feature set.