Paper Details: Downloads: 816
Serial Number: P1151025145
Title: Efficient DIS Based Region Growing Segmentation Technique for VHR Satellite Images
Authors: Ashwini Kunte and Anjali Bhalchandra
Abstract: Image segmentation is typically used to locate objects and boundaries such as lines, curves, regions etc in images. Recent day’s segmentation is used extensively in automated image analysis. The ultimate aim of this analysis is to extract important features from the image data, from which description, interpretation or understanding of the scene can be provided by the machine. This task becomes difficult while dealing with high resolution imagery due to superfluous details, too many objects and possibly low contrast ratio present in the imagery. As there is tremendous advancements in imaging techniques higher and higher resolution imagery is becoming available. Thus there is constant need of refined algorithms for image segmentation which is first step of image analysis. In this paper we propose a novel approach of using Difference in Strength Map (DIS) for region growing segmentation. Further in the paper we investigate its effectiveness for 0.5 meter resolution World View1 imagery. We also compare its results with other segmentation techniques such as simple region growing, fusion of edge and region growing.
Keywords: Difference in strength (DIS), region grow, edge guided region growing
Journal/Conference: International Journal of Graphics, Vision and Image Processing
Volume: 10
Issue: 3
Submission Date: 6/13/2010 12:00:00 AM
Review Date: 7/4/2010 12:00:00 AM
Publishing Date: 7/22/2010 12:00:00 AM
Article Downloads: 816
Download:

Facebook