Unsupervised segmentation of text fragments in real scenes

Authors:
Leonardo M. B. Claudino;Antônio de P. Braga;Arnaldo de A. Araújo;André F. Oliveira
Affiliations:
Centro de Pesquisa e Desenvolvimento em Engenharia Elétrica, Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil;Centro de Pesquisa e Desenvolvimento em Engenharia Elétrica, Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil;Depto. de Ciência da Computação, Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil;Depto. de Ciência da Computação, Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil
Venue:
ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing
Year:
2005

Citing 3
Cited 1

TextFinder: An Automatic System to Detect and Recognize Text In Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiscale Segmentation of Unstructured Document Pages Using Soft Decision Integration

IEEE Transactions on Pattern Analysis and Machine Intelligence
Detection of Text Marks on Moving Vehicles

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

Parallel image segmentation in reconfigurable chip multiprocessors

ISPA'06 Proceedings of the 2006 international conference on Frontiers of High Performance Computing and Networking

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a method that aims to reduce a real scene to a set of regions that contain text fragments and keep small number of false positives. Text is modeled and characterized as a texture pattern, by employing the QMF wavelet decomposition as a texture feature extractor. Processing includes segmentation and spatial selection of regions and then content-based selection of fragments. Unlike many previous works, text fragments in different scales and resolutions laid against complex backgrounds are segmented without supervision. Tested in four image databases, the method is able to reduce visual noise to 4.69% and reaches 96.5% of coherency between the localized fragments and those generated by manual segmentation.