Optimization of the Gaussian Kernel Extended by Binary Morphology for Text Line Segmentation
Loading...
Date
2010-12
Authors
ORCID
Advisor
Referee
Mark
Journal Title
Journal ISSN
Volume Title
Publisher
Společnost pro radioelektronické inženýrství
Abstract
In this paper, an approach for text line segmentation by algorithm with the implementation of the Gaussian kernel is presented. As a result of algorithm, the growing area around text is exploited for text line segmentation. To improve text line segmentation process, isotropic Gaussian kernel is extended by dilatation. Furthermore, algorithms with isotropic and extended Gaussian kernels are examined and evaluated under different text samples. Results are given and comparative analysis is made for these algorithms. From the obtained results, optimization of the parameters defining extended Gaussian kernel dimension is proposed. The presented algorithm with the extended Gaussian kernel showed robustness for different types of text samples.
Description
Citation
Radioengineering. 2010, vol. 19, č. 4, s. 718-724. ISSN 1210-2512
http://www.radioeng.cz/fulltexts/2010/10_04_718_724.pdf
http://www.radioeng.cz/fulltexts/2010/10_04_718_724.pdf
Document type
Peer-reviewed
Document version
Published version
Date of access to the full text
Language of document
en