User-Assisted Archive Document Image Analysis for Digital Library Construction

Authors:
J. He;A. C. Downton
Affiliations:
-;-
Venue:
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Year:
2003

Citing 3
Cited 8

Recursive X-Y cut using bounding boxes of connected components

ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2) - Volume 2
A Handwriting Understanding Environment (HUE) for Rapid Prototyping in Handwriting and Document Analysis Research

ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
Computerising Natural History Card Archives

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1

Computerising Natural History Card Archives

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
An Adaptative Recognition System Using a Table Description Language for Hierarchical Table Structures in Archival Documents

Graphics Recognition. Recent Advances and New Opportunities
Handwritten Chinese text line segmentation by clustering with distance metric learning

Pattern Recognition
Segmentation of historical machine-printed documents using Adaptive Run Length Smoothing and skeleton segmentation paths

Image and Vision Computing
Text line segmentation for gray scale historical document images

Proceedings of the 2011 Workshop on Historical Document Imaging and Processing
A minimal and sufficient way of introducing external knowledge for table recognition in archival documents

GREC'05 Proceedings of the 6th international conference on Graphics Recognition: ten Years Review and Future Perspectives
Text line extraction for historical document images

Pattern Recognition Letters
Intangible cultural heritage preservation: An exploratory study of digitization of the historical literature of Chinese Kunqu opera librettos

Journal on Computing and Cultural Heritage (JOCCH)

Quantified Score

Hi-index	0.00

Visualization

Abstract

A configurable archive document image analysissystem for digital library construction has been designedusing rapid prototyping and top-down iterativedevelopment methods. This approach has been found tobe essential in order to capture the curators' expertiseabout existing card archive structures, content anddatabases. The design currently achieves about 93%correct segmentation of the required archive card fieldsoverall, with 81.3% of all archive cards in a testset of2000 images having all fields correctly segmented andlabelled. Analysis of errors in the testset indicates thatheavily-annotated cards and non-standard card formatscomprise 5-10% of the overall archive, and a significantproportion of these are unlikely to be resolvable withoutcuratorial intervention.