Main Article Content

SAADI Bin Ahmad Kamaruddin
International Islamic University Malaysia
Malaysia
Nor AZURA MD Ghanib
Universiti Teknologi MARA
Malaysia
Choong-Yeun Liong
Universiti Kebangsaan Malaysia
Malaysia
Abdul AZIZ Jemain
Universiti Kebangsaan Malaysia
Malaysia
Vol. 1 No. 3 (2012), Articles, pages 27-34
DOI: https://doi.org/10.14201/ADCAIJ20121312734
Accepted: Jul 1, 2013
Copyright

Abstract

This paper implements two layer neural networks with different feedforward backpropagation algorithms for better performance of firearm classification us-ing numerical features from the ring image. A total of 747 ring images which are extracted from centre of the firing pin impression have been captured from five different pistols of the Parabellum Vector SPI 9mm model. Then, based on finding from the previous studies, the six best geometric moments numerical fea-tures were extracted from those ring images. The elements of the dataset were further randomly divided into the training set (523 elements), testing set (112 el-ements) and validation set (112 elements) in accordance with the requirement of the supervised learning nature of the backpropagation neural network (BPNN). Empirical results show that a two layer BPNN with a 6-7-5 configura-tion and tansig/tansig transfer functions with ‘trainscg’ training algorithm has produced the best classification result of 98%. The classification result is an improvement compared to the previous studies as well as confirming that the ring image region contains useful information for firearm classification.

Downloads

Download data is not yet available.

Article Details

References

BONFANTI, M. S. and KINDER, J. D. The Influence of Manufacturing Processes on the Identification of Bullets and Cartridge Cases- A Review of the Literature. Journal of Science and Justice, 1999.

BURRARD, G. Identification of Firearms and Forensic Ballistics. Herbert Jenkins, 1951. London

DEMUTH, H. and BEALE, M. Neural Network for Use with MATLAB. Version Four, 3 Apple Hill Drive, Natick, MA, TheMathWorks, 2001. United States

EBERHART, R. C. and DOBBINS, R. W. Neural Network PC Tools: A Practical Guide. California Academic Press, 1990. San Diego

GERADTS, Z., BIJHOLD, J., HERMSEN, R. and MURTAGH, F. Image Matching Algorithms for Breech Face Marks and Firing Pin in a Database of Spent Cartridge Cases of Firearms. Forensic Science International, 2001.

GERADTS, Z., BIJHOLD, J., HERMSEN, R. and MURTAGH, F. Pattern Recognition in a Database of Cartridge Cases.

Proceedings of The International Society for Optical Engineering: Investigation and Forensic Science Technologies, 1999. Kathleen Higgins.

GHANI, N. A. M., LIONG, C.-Y. and JEMAIN, A. A. Extraction and Selection of Basic Statistical Features for Forensic Ballistic Specimen Identification (in Malay). Sains Malaysiana, 2009a.

GHANI, N. A. M., LIONG, C.-Y. and JEMAIN, A. A. Analysis of Geometric Moments as Features for Identification of Forensic Ballistics Specimen. Lecture Notes in Computer Science 5518, Springer, 2009b. Berlin.

GHANI, N. A. M., LIONG, C.-Y. and JEMAIN, A. A. Analysis of Geometric Moments as Features for Firearm Identification.

Forensic Science International, 2010.

KAMARUDDIN, S. A., GHANI, N. A. M., LIONG, C.-Y. and JEMAIN, A. A. Firearm recognition based on whole firing pin impression image via back propagaion neural network.

Proceedings of Institute of Electrical and Electronics Engineers: International Conference on Pattern Analysis and Intelligent Robotics, 2011.

KONG, J., LI, D. G. and WATSON, A. C. A Firearm Identification Sysytem based on Neural Network. Journal of Computer Science, 2003.

KOU, C., TUNG, C. T. and FU, H. C. Firearms Identification based on SOFM Model of Neural Network. Journal of Security Technology, 1994.

LENG, J. and HUANG, Z. On Analysis of Circle Moments and Texture Features for Cartridge Images Recognition. Expert Systems with Applications 39, 2012.

LI, D. A New Approach for Firearm Identification with Hierarchical Neural networks based on Cartridge Case Images. Journal of Forensic Science International, 2006.

MASTERS, T. Practical Neural Network Recipes in C++. Academic Press, 1993. San Diego.

PANCA, M. R., MOCH, R. and NANANG, S. The Implementation of Feedforward Backpropagation Algorithm for Digit Handwritten Recognition in a Xilinx Spartan-3. Jurnal Electrics Electronics Communication Controls Informatics Systems, 2010.

SMITH, C. L. and CROSS, J. M. Optical imaging techniques for ballistics specimens to identify firearms. Proceedings of Institute of Electrical and Electronics Engineers: International Carnahan Conference on Security Technology, 1995.

SMITH, C. L. and LI, D. Intelligent imaging of forensic ballistics specimens for ID. Proceedings of Institute of Electrical and Electronics Engineers: Congress on Image and Signal Processing, 2008.

SMITH, C. L., CROSS, J. M. and VARIYAN, G. J. FIREBALL: An Interactive Database for the Forensic Ballistic Identification of Firearms. Research Report, Australian Institute of Security and Applied Technology, Edith Cowan University, 1995. Western Australia.

WIDROW, B., RUMELHART, D. and LEHR, M.A. Neural Networks: Applications in Industry, Business, and Science. Communications of the Association for Computing Machinery, 1994.

XIN, L.P., ZHOU, J. and RONG, G. A Cartridge Identification System for Firearms Authentication. Proceedings of the 5th International Conference on Signal Processing, WCCC ICSP 2000, 2000.