doi: 10.7763/IJFCC.2014.V3.341
Semantic Concepts Classification on Outdoor Scene Images Based on Region-Based Approach
Kyawt Kyawt Htay
,
Nyein Aye
- University of Computer Studies, Mandalay, Myanmar.
Abstract
Outdoor scene analysis is a complex problem forboth image processing and pattern recognition domains. Thereare two methods of segmenting images to look for objects in animage, block-based and region-based. Region-based method canprovide some useful information about objects even thoughsegmentation may not be perfect. There are three phases in thissystem: segmentation, features extraction and classification.The basic idea of this system is to classify local image regionsinto semantic concept classes such as tree, sky and road etc. Inthis paper, modified Marker-Controlled Watershed (MCWS)algorithm is proposed. Firstly, the modified (MCWS) algorithmis used to segment input image. And then, texture featurevectors are extracted from segmented regions by Gray-LevelCo-occurrence Matrix (GLCM). Finally, classification isperformed by 3-layer Artificial Neural Network (ANN). Thissystem is applied on real scene images dataset.
Keywords
- Marker-controlled watershed
- outdoor sceneanalysis
- texture
How to Cite
Kyawt Kyawt Htay and Nyein Aye, "Semantic Concepts Classification on Outdoor Scene Images Based on Region-Based Approach," International Journal of Future Computer and Communication, vol. 3, no. 6, pp. 427-431, 2014. https://doi.org/ 10.7763/IJFCC.2014.V3.341
Copyright & License
Copyright © 2014 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).