Unique Measure for Geometrical Shape Object Detection-based on Area Matching

  • Debasis Chaudhuri Defence Electronics Application Laboratory, Dehradun
  • N. K. Kushwaha Defence Electronics Application Laboratory, Dehradun
  • I. Sharif Defence Electronics Application Laboratory, Dehradun
  • V. Gohri Defence Electronics Application Laboratory, Dehradun
DOI: https://doi.org/10.14429/dsj.62.942
Keywords: Measure, shape detection, pattern recognition, circular fit, elliptic fit, rectangular fit

Abstract

Object classifier often operates by making decisions based on the values of several shape properties measured from an image of the object. The paper introduces a unique definition of measure for 2-D geometrical object shape detection. Using this definition different object shapes can be identified on the basis of their degree of fitness parameter. Basically, we have fitted a 2-D polygon/curve on the object as a best fitted polygon/curve and computed the parameter degree of fitness which is the ratio of the matching area and non-matching area due to the fitted polygon/curve and the object both. The results show the effectiveness of the proposed measure.

Defence Science Journal, 2012, 62(1), pp.58-66, DOI:http://dx.doi.org/10.14429/dsj.62.942

Author Biographies

Debasis Chaudhuri, Defence Electronics Application Laboratory, Dehradun

Dr D. Chaudhuri received his MSc (Applied Mathematics) from Jadavpur university, Kolkata in 1987 and PhD (Image Processing and Pattern Recognition) from Indian Statistical Institute, Kolkata in 1994. Currently, working as Scientist with the Defence Electronics Applications Laboratory (DEAL), Dehradun, India. He has published over 45 papers in international journals and conferences. His research interests include: Image processing, pattern recognition, computer vision, remote sensing and target detection from satellite imagery.

N. K. Kushwaha, Defence Electronics Application Laboratory, Dehradun
Mr N.K. Kushwaha received his BTech (Computer Science and Engineering) from Indian Institute of Technology, Kanpur in 2009. Presently, he is a scientist at DEAL, Dehradun. His fields of interest include: Image processing, pattern recognition, computer vision and remote sensing.
I. Sharif, Defence Electronics Application Laboratory, Dehradun
Mr Imran Sharif received his BTech (Computer Science and Engineering) from Institute of Engineering and Technology, Kanpur in 2002 and MTech from CDAC, Noida in 2005. Currently, he is pursuing PhD from Uttarakhand Technical University, Dehradun. Presently working as a scientist at DEAL, Dehradun. His fields of interest include: Hyper spectral image processing, pattern recognition, computer vision, and remote sensing.
V. Gohri, Defence Electronics Application Laboratory, Dehradun
Mr V Gohri retired as Scientist ‘G’ from DEAL, Dehradun. He developed technique for generation of reference image (simulated radar image) in X-band and Ka-band for missile terminal guidance. More than 30 years research  experience in the field of remote sensing, optical image processing, digital image processing, sar image processing, and radar image simulation. He has published 18 papers in international and national journals and conferences. He is a fellow IETE and a member of CSI.
Published
2012-01-23
How to Cite
Chaudhuri, D., Kushwaha, N., Sharif, I., & Gohri, V. (2012). Unique Measure for Geometrical Shape Object Detection-based on Area Matching. Defence Science Journal, 62(1), 58-66. https://doi.org/10.14429/dsj.62.942
Issue
Vol 62 No 1: Cryptology and Communication Security
Section
Research Papers
Copyright (c) 2016 Defence Science Journal

 Where otherwise noted, the Articles on this site are licensed under Creative Commons License: CC Attribution-Noncommercial-No Derivative Works 2.5 India