Analysis and interpretation of segmentation techniques based on delaunay triangulation and iterative thresholding explicitly used for detection of anti-personnel landmines

摘要

This paper deals with an attempt to detect anti-personnel landmines from images acquired in the visible spectrum. Segmentation techniques used includes Iterative Thresholding and Delaunay Triangulation using Morphological Thinning. Homomorphic Filtering is used for image pre-processing. Results have been tabulated and statistical parameters have been calculated from the gray level co-occurrence matrix. Iterative thresholding proved to be a better segmentation technique than Delaunay Triangulation. This work provides the basis for future analysis.