Firearm classification based on numerical features of the firing pin impression

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

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

1 Citation (Scopus)

Abstract

Many heavy crimes committed such as murders or robberies frequently involve firearms, particularly pistols. In order to solve the crime cases, firearm identification is becoming vital. Unique marks are left on the bullet and the cartridge case when a firearm is fired. The firing pin impression is one of the most vital marks on any cartridge case. In this study, a total of 68 features of firing pin impression images - 20 basic statistical features, and 48 geometric moment features up to the sixth order - were extracted from three regions of the firing pin impression image, namely whole, centre and ring images. Five different types of pistol of the Parabellum Vector SPI 9 mm model were tested, where 50 bullets were fired from each pistol. Preliminary analysis using Pearson correlation shows that the features are significantly highly correlated. Therefore principal component analysis (PCA) was used to analyze the interrelationship among the features and combine them into a smaller set of factors while maintaining maximum information of the original patterns. PCA has reduced the dimensionality of the features into nine significant components of features. Discriminant analysis was used to identify the types of pistols used based on the new components. A total of 85.2% of the images were correctly classified according to the pistols used using cross-validation under discriminant analysis. The result demonstrates the potential of using PCA to reduce the dimensions of the numerical features towards an efficient firearm identification system.

Original languageEnglish
Title of host publicationProcedia Computer Science
PublisherElsevier
Pages144-151
Number of pages8
Volume13
DOIs
Publication statusPublished - 2012
Event3rd International Neural Network Society Winter Conference, INNS-WC 2012 - Bangkok, Thailand
Duration: 3 Oct 20125 Oct 2012

Other

Other3rd International Neural Network Society Winter Conference, INNS-WC 2012
CountryThailand
CityBangkok
Period3/10/125/10/12

Fingerprint

Principal component analysis
Crime
Discriminant analysis
Identification (control systems)

Keywords

  • Firearm identification
  • Firing pin impression
  • Geometric moment
  • Principal component analysis
  • Statistical features

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Liong, C. Y., Md Ghani, N. A., Kamaruddin, S. B. A., & Jemain, A. A. (2012). Firearm classification based on numerical features of the firing pin impression. In Procedia Computer Science (Vol. 13, pp. 144-151). Elsevier. https://doi.org/10.1016/j.procs.2012.09.123

Firearm classification based on numerical features of the firing pin impression. / Liong, Choong Yeun; Md Ghani, Nor Azura; Kamaruddin, Saadi Bin Ahmad; Jemain, Abdul Aziz.

Procedia Computer Science. Vol. 13 Elsevier, 2012. p. 144-151.

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

Liong, CY, Md Ghani, NA, Kamaruddin, SBA & Jemain, AA 2012, Firearm classification based on numerical features of the firing pin impression. in Procedia Computer Science. vol. 13, Elsevier, pp. 144-151, 3rd International Neural Network Society Winter Conference, INNS-WC 2012, Bangkok, Thailand, 3/10/12. https://doi.org/10.1016/j.procs.2012.09.123
Liong CY, Md Ghani NA, Kamaruddin SBA, Jemain AA. Firearm classification based on numerical features of the firing pin impression. In Procedia Computer Science. Vol. 13. Elsevier. 2012. p. 144-151 https://doi.org/10.1016/j.procs.2012.09.123
Liong, Choong Yeun ; Md Ghani, Nor Azura ; Kamaruddin, Saadi Bin Ahmad ; Jemain, Abdul Aziz. / Firearm classification based on numerical features of the firing pin impression. Procedia Computer Science. Vol. 13 Elsevier, 2012. pp. 144-151
@inproceedings{22cb09c7c54e46e08976aaa6dd67aaee,
title = "Firearm classification based on numerical features of the firing pin impression",
abstract = "Many heavy crimes committed such as murders or robberies frequently involve firearms, particularly pistols. In order to solve the crime cases, firearm identification is becoming vital. Unique marks are left on the bullet and the cartridge case when a firearm is fired. The firing pin impression is one of the most vital marks on any cartridge case. In this study, a total of 68 features of firing pin impression images - 20 basic statistical features, and 48 geometric moment features up to the sixth order - were extracted from three regions of the firing pin impression image, namely whole, centre and ring images. Five different types of pistol of the Parabellum Vector SPI 9 mm model were tested, where 50 bullets were fired from each pistol. Preliminary analysis using Pearson correlation shows that the features are significantly highly correlated. Therefore principal component analysis (PCA) was used to analyze the interrelationship among the features and combine them into a smaller set of factors while maintaining maximum information of the original patterns. PCA has reduced the dimensionality of the features into nine significant components of features. Discriminant analysis was used to identify the types of pistols used based on the new components. A total of 85.2{\%} of the images were correctly classified according to the pistols used using cross-validation under discriminant analysis. The result demonstrates the potential of using PCA to reduce the dimensions of the numerical features towards an efficient firearm identification system.",
keywords = "Firearm identification, Firing pin impression, Geometric moment, Principal component analysis, Statistical features",
author = "Liong, {Choong Yeun} and {Md Ghani}, {Nor Azura} and Kamaruddin, {Saadi Bin Ahmad} and Jemain, {Abdul Aziz}",
year = "2012",
doi = "10.1016/j.procs.2012.09.123",
language = "English",
volume = "13",
pages = "144--151",
booktitle = "Procedia Computer Science",
publisher = "Elsevier",

}

TY - GEN

T1 - Firearm classification based on numerical features of the firing pin impression

AU - Liong, Choong Yeun

AU - Md Ghani, Nor Azura

AU - Kamaruddin, Saadi Bin Ahmad

AU - Jemain, Abdul Aziz

PY - 2012

Y1 - 2012

N2 - Many heavy crimes committed such as murders or robberies frequently involve firearms, particularly pistols. In order to solve the crime cases, firearm identification is becoming vital. Unique marks are left on the bullet and the cartridge case when a firearm is fired. The firing pin impression is one of the most vital marks on any cartridge case. In this study, a total of 68 features of firing pin impression images - 20 basic statistical features, and 48 geometric moment features up to the sixth order - were extracted from three regions of the firing pin impression image, namely whole, centre and ring images. Five different types of pistol of the Parabellum Vector SPI 9 mm model were tested, where 50 bullets were fired from each pistol. Preliminary analysis using Pearson correlation shows that the features are significantly highly correlated. Therefore principal component analysis (PCA) was used to analyze the interrelationship among the features and combine them into a smaller set of factors while maintaining maximum information of the original patterns. PCA has reduced the dimensionality of the features into nine significant components of features. Discriminant analysis was used to identify the types of pistols used based on the new components. A total of 85.2% of the images were correctly classified according to the pistols used using cross-validation under discriminant analysis. The result demonstrates the potential of using PCA to reduce the dimensions of the numerical features towards an efficient firearm identification system.

AB - Many heavy crimes committed such as murders or robberies frequently involve firearms, particularly pistols. In order to solve the crime cases, firearm identification is becoming vital. Unique marks are left on the bullet and the cartridge case when a firearm is fired. The firing pin impression is one of the most vital marks on any cartridge case. In this study, a total of 68 features of firing pin impression images - 20 basic statistical features, and 48 geometric moment features up to the sixth order - were extracted from three regions of the firing pin impression image, namely whole, centre and ring images. Five different types of pistol of the Parabellum Vector SPI 9 mm model were tested, where 50 bullets were fired from each pistol. Preliminary analysis using Pearson correlation shows that the features are significantly highly correlated. Therefore principal component analysis (PCA) was used to analyze the interrelationship among the features and combine them into a smaller set of factors while maintaining maximum information of the original patterns. PCA has reduced the dimensionality of the features into nine significant components of features. Discriminant analysis was used to identify the types of pistols used based on the new components. A total of 85.2% of the images were correctly classified according to the pistols used using cross-validation under discriminant analysis. The result demonstrates the potential of using PCA to reduce the dimensions of the numerical features towards an efficient firearm identification system.

KW - Firearm identification

KW - Firing pin impression

KW - Geometric moment

KW - Principal component analysis

KW - Statistical features

UR - http://www.scopus.com/inward/record.url?scp=84897992185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897992185&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2012.09.123

DO - 10.1016/j.procs.2012.09.123

M3 - Conference contribution

AN - SCOPUS:84897992185

VL - 13

SP - 144

EP - 151

BT - Procedia Computer Science

PB - Elsevier

ER -