Home > Archive > 2020 > Volume 10 Number 5 (Sept. 2020) >
IJMLC 2020 Vol.10(5): 707-713 ISSN: 2010-3700
DOI: 10.18178/ijmlc.2020.10.5.994

Imaging Analysis of Steel Rod Shrapnel Using Artificial Neural Networks

Kittiya Poonsilp

Abstract—The purpose of this study was to analyse the explosive forensic data contained in digital image. The explosive forensic data used in this study was mainly targeted on the cross-section image of steel rod shrapnel. Digital image processing techniques were used to find the areas and types of the shrapnel. The process began with imaging segmentation to find the boundary box of the shrapnel area and then extracted the areas which contained key features and computed the statistical values of those areas, Finally, the statistical values were administered to the Artificial Neural Network to classify the types of shrapnel. The results showed 71% accuracy which was acceptable since each type of cross-section image had a very slightly different and much different to detect by human eyes.

Index Terms—Explosive ordnance disposal, neural network, shrapnel, steel rod.

Kittiya Poonsilp is with the Department of Computer Science, Suan Sunandha Rajabhat University, Bangkok, Thailand (e-mail: kittiya.po@ssru.ac.th).

[PDF]

Cite: Kittiya Poonsilp, "Imaging Analysis of Steel Rod Shrapnel Using Artificial Neural Networks," International Journal of Machine Learning and Computing vol. 10, no. 5, pp. 707-713, 2020.

Copyright © 2020 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).

General Information

  • ISSN: 2010-3700 (Online)
  • Abbreviated Title: Int. J. Mach. Learn. Comput.
  • Frequency: Bimonthly
  • DOI: 10.18178/IJMLC
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals Library.
  • E-mail: ijmlc@ejournal.net


Article Metrics