Newspaper document analysis featuring connected line segmentation

Authors:
Phillip E. Mitchell;Hong Yan
Affiliations:
School of Electrical and Information Engineering, University of Sydney, NSW 2006;Department of Electronic Engineering, City University of Hong Kong, Kowloon, Hong Kong
Venue:
VIP '01 Proceedings of the Pan-Sydney area workshop on Visual information processing - Volume 11
Year:
2001

Citing 6
Cited 0

Page segmentation using the description of the background

Computer Vision and Image Understanding - Special issue on document image understanding and retrieval
Document page decomposition by the bounding-box project

ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2) - Volume 2
Page segmentation and classification utilising a bottom-up approach

ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2) - Volume 2
Location of name and address on fax cover pages

ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2) - Volume 2
Layout Analysis of Complex Documents

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 4
Parameter-Independent Geometric Document Layout Analysis

ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 4

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an algorithm designed to segment and classify newspaper documents. A notable feature of this algorithm is the ability to detect lines in the document - including lines that are connected to other components. A bottom-up approach is used to segment the image into patterns, and then each pattern is classified into one of seven types. Complete regions are then formed from the classified patterns.