International Journal of Image, Graphics and Signal Processing (IJIGSP)
IJIGSP Vol. 5, No. 3, 8 Mar. 2013
Cover page and Table of Contents: PDF (size: 537KB)
An Improved Convexity Based Segmentation Algorithm for Heavily Camouflaged Images
Full Text (PDF, 537KB), PP.55-63
Views: 0 Downloads: 0
Author(s)
Amarjot Singh
1,*
N Sumanth Kumar
1
Index Terms
Convexity, Camouflage, Sobel, Roberts, Canny, Edge Detection
Abstract
The paper proposes an advanced convexity based segmentation algorithm for heavily camouflaged images. The convexity of the intensity function is used to detect camouflaged objects from complex environments. We take advantage of operator for the detection of 3D concave or convex graylevels to exhibit the effectiveness of camouflage breaking based on convexity. The biological motivation behind operator and its high robustness make it suitable for camouflage breaking. The traditional convexity based algorithm identifies the desired targets but in addition also identifies sub-targets due to their three dimensional behavior. The problem is overcome by combining the conventional algorithm with thresholding. The proposed method is able to eliminate the sub-targets leaving behind only the target of interest in the input image. The proposed method is compared with the conventional operator. It is also compared with some conventional edge based operator for performance evaluation.
Cite This Paper
Amarjot Singh, N Sumanth Kumar,"An Improved Convexity Based Segmentation Algorithm for Heavily Camouflaged Images", IJIGSP, vol.5, no.3, pp.55-63, 2013. DOI: 10.5815/ijigsp.2013.03.08
Reference
[1]A. C. Copeland and M. M. Trivedi. Models and metrics for signature strength evaluation of camouflaged targets. Proceedings of the SPIE, 3070:194{199, 1997.
[2]G. E. Irvin and M. G. Dowler. Physiologically based computational approach to camouflage and masking patterns. Proceedings of SPIE, 1700:481{488, 1992.
[3]F. M. Gretzmacher, G. S. Ruppert, and S. Nyberg. Camouflage assessment considering humanperception data. Proceedings of the SPIE, 3375:58{67, 1998.
[4]L. B. Hepinger. Camouflage simulation and effectiveness assessment for the individual soldier. Proceedings of SPIE, 1311:277{283, 1990.
[5]I. V. Ternovskiy and T. Jannson. Mapping-singularities-based motion estimation. Proceedings of the SPIE, 3173:317{321, 1997.
[6]S. Marouani, A. Huertas, and G. Medioni. Model-based aircraft recognition in perspective aerial imagery. In Proceedings of the International Symposium on Computer Vision, pages 371{376, Coral Gables, Florida, USA, November 1995.
[7]Ariel Tankus and Yehezkel Yeshurun, "Convexity-based Visual Camouflage Breaking" Supported by grants from: Minerva Minkowski center for geometry, Israel Academy of Science for Geometric Computing, and the Moscona fund.