Firearm recognition based on whole firing pin impression image via backpropagation neural network

Saadi Bin Ahmad Kamaruddin, Nor Azura Md Ghani, Choong Yeun Liong, Abdul Aziz Jemain

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Firearms identification is a vital aim of firearm analysis. The firing pin impression image on a cartridge case from a fired bullet is one of the most significant clues in firearms identification. In this study, a set of data which focused on selected 6 features of firing pin impression images before an entirety of five different pistols of South African made; the Parabellum Vector SPI 9mm model, were used. The numerical features are geometric moments of whole image computed from a total of 747 cartridge case images. Under pattern recognition theory, the supervised features of firing pin impression images were then trained and validated using a two-layer backpropagation neural network (BPNN) design with computed hidden layers. A two-layer 6-7-5 connections BPNN of sigmoid/linear transfer functions with trainlm algorithm was found to yield the best classification result using cross-validation, where 96% of the images were correctly classified according to the pistols used. Moreover, the network was trained under very small mean-square error (MSE=0.01). This means that neural network method is capable to learn and validate well the numerical features of whole firing pin impression with high precision and fast classification results.

Original languageEnglish
Title of host publicationProceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011
Pages177-182
Number of pages6
Volume1
DOIs
Publication statusPublished - 2011
Event2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011 - Putrajaya
Duration: 28 Jun 201129 Jun 2011

Other

Other2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011
CityPutrajaya
Period28/6/1129/6/11

Fingerprint

Backpropagation
Neural networks
Mean square error
Pattern recognition
Transfer functions

Keywords

  • backpropagation neural network (BPNN)
  • firearm analysis
  • firearm identification
  • forensic ballistics
  • geometric moment

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Cite this

Kamaruddin, S. B. A., Ghani, N. A. M., Liong, C. Y., & Jemain, A. A. (2011). Firearm recognition based on whole firing pin impression image via backpropagation neural network. In Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011 (Vol. 1, pp. 177-182). [5976891] https://doi.org/10.1109/ICPAIR.2011.5976891

Firearm recognition based on whole firing pin impression image via backpropagation neural network. / Kamaruddin, Saadi Bin Ahmad; Ghani, Nor Azura Md; Liong, Choong Yeun; Jemain, Abdul Aziz.

Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011. Vol. 1 2011. p. 177-182 5976891.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kamaruddin, SBA, Ghani, NAM, Liong, CY & Jemain, AA 2011, Firearm recognition based on whole firing pin impression image via backpropagation neural network. in Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011. vol. 1, 5976891, pp. 177-182, 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011, Putrajaya, 28/6/11. https://doi.org/10.1109/ICPAIR.2011.5976891
Kamaruddin SBA, Ghani NAM, Liong CY, Jemain AA. Firearm recognition based on whole firing pin impression image via backpropagation neural network. In Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011. Vol. 1. 2011. p. 177-182. 5976891 https://doi.org/10.1109/ICPAIR.2011.5976891
Kamaruddin, Saadi Bin Ahmad ; Ghani, Nor Azura Md ; Liong, Choong Yeun ; Jemain, Abdul Aziz. / Firearm recognition based on whole firing pin impression image via backpropagation neural network. Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011. Vol. 1 2011. pp. 177-182
@inproceedings{7b6ba248560440d286aa8ae8a0abb605,
title = "Firearm recognition based on whole firing pin impression image via backpropagation neural network",
abstract = "Firearms identification is a vital aim of firearm analysis. The firing pin impression image on a cartridge case from a fired bullet is one of the most significant clues in firearms identification. In this study, a set of data which focused on selected 6 features of firing pin impression images before an entirety of five different pistols of South African made; the Parabellum Vector SPI 9mm model, were used. The numerical features are geometric moments of whole image computed from a total of 747 cartridge case images. Under pattern recognition theory, the supervised features of firing pin impression images were then trained and validated using a two-layer backpropagation neural network (BPNN) design with computed hidden layers. A two-layer 6-7-5 connections BPNN of sigmoid/linear transfer functions with trainlm algorithm was found to yield the best classification result using cross-validation, where 96{\%} of the images were correctly classified according to the pistols used. Moreover, the network was trained under very small mean-square error (MSE=0.01). This means that neural network method is capable to learn and validate well the numerical features of whole firing pin impression with high precision and fast classification results.",
keywords = "backpropagation neural network (BPNN), firearm analysis, firearm identification, forensic ballistics, geometric moment",
author = "Kamaruddin, {Saadi Bin Ahmad} and Ghani, {Nor Azura Md} and Liong, {Choong Yeun} and Jemain, {Abdul Aziz}",
year = "2011",
doi = "10.1109/ICPAIR.2011.5976891",
language = "English",
isbn = "9781612844046",
volume = "1",
pages = "177--182",
booktitle = "Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011",

}

TY - GEN

T1 - Firearm recognition based on whole firing pin impression image via backpropagation neural network

AU - Kamaruddin, Saadi Bin Ahmad

AU - Ghani, Nor Azura Md

AU - Liong, Choong Yeun

AU - Jemain, Abdul Aziz

PY - 2011

Y1 - 2011

N2 - Firearms identification is a vital aim of firearm analysis. The firing pin impression image on a cartridge case from a fired bullet is one of the most significant clues in firearms identification. In this study, a set of data which focused on selected 6 features of firing pin impression images before an entirety of five different pistols of South African made; the Parabellum Vector SPI 9mm model, were used. The numerical features are geometric moments of whole image computed from a total of 747 cartridge case images. Under pattern recognition theory, the supervised features of firing pin impression images were then trained and validated using a two-layer backpropagation neural network (BPNN) design with computed hidden layers. A two-layer 6-7-5 connections BPNN of sigmoid/linear transfer functions with trainlm algorithm was found to yield the best classification result using cross-validation, where 96% of the images were correctly classified according to the pistols used. Moreover, the network was trained under very small mean-square error (MSE=0.01). This means that neural network method is capable to learn and validate well the numerical features of whole firing pin impression with high precision and fast classification results.

AB - Firearms identification is a vital aim of firearm analysis. The firing pin impression image on a cartridge case from a fired bullet is one of the most significant clues in firearms identification. In this study, a set of data which focused on selected 6 features of firing pin impression images before an entirety of five different pistols of South African made; the Parabellum Vector SPI 9mm model, were used. The numerical features are geometric moments of whole image computed from a total of 747 cartridge case images. Under pattern recognition theory, the supervised features of firing pin impression images were then trained and validated using a two-layer backpropagation neural network (BPNN) design with computed hidden layers. A two-layer 6-7-5 connections BPNN of sigmoid/linear transfer functions with trainlm algorithm was found to yield the best classification result using cross-validation, where 96% of the images were correctly classified according to the pistols used. Moreover, the network was trained under very small mean-square error (MSE=0.01). This means that neural network method is capable to learn and validate well the numerical features of whole firing pin impression with high precision and fast classification results.

KW - backpropagation neural network (BPNN)

KW - firearm analysis

KW - firearm identification

KW - forensic ballistics

KW - geometric moment

UR - http://www.scopus.com/inward/record.url?scp=80052192084&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052192084&partnerID=8YFLogxK

U2 - 10.1109/ICPAIR.2011.5976891

DO - 10.1109/ICPAIR.2011.5976891

M3 - Conference contribution

SN - 9781612844046

VL - 1

SP - 177

EP - 182

BT - Proceedings of the 2011 International Conference on Pattern Analysis and Intelligent Robotics, ICPAIR 2011

ER -