C# Implementation of Split and Merge Algorithm for Image Segmentation

Iordanov, Velin and Draganov, Ivo (2018) C# Implementation of Split and Merge Algorithm for Image Segmentation. In: 53rd International Scientific Conference on Information, Communication and Energy Systems and Technologies (ICEST 2018), June 28-30, 2018, Sozopol, Bulgaria.

[img]
Preview
Text
ICEST2018_29.pdf

Download (454kB) | Preview
Official URL: http://icestconf.org/wp-content/uploads/2018/07/IC...

Abstract

In this paper, we propose a C# implementation of the split and merge algorithm with a main applicability directed towards image segmentation. The algorithm process color and grayscale images by splitting them following quad-tree decomposition over intensity homogeneity criterion. Then adjacent blocks, including such from different tree levels, are merged together to form candidate regions for segmentation. Area filtration of the regions is the final processing step prior to generating the output map of the application. Testing is done with images containing printed text over complex background and promising results are registered.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Image Segmentation, Split and Merge, C#, Area Filtration, Text Extraction
Subjects: Scientific Fields (Frascati) > Engineering and Technology > Electrical engineering, electronic engineering,information engineering
Divisions: Faculty of Technical Sciences
Depositing User: ICEST
Date Deposited: 18 Mar 2020 17:08
Last Modified: 18 Mar 2020 17:08
URI: http://eprints.uklo.edu.mk/id/eprint/4245

Actions (login required)

View Item View Item