Firearm identification using numerical features of centre firing pin impression image

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

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

3 Citations (Scopus)

Abstract

There are many crime cases such as murders or robberies which frequently involve firearms, especially pistols. The centre firing pin impression image on a cartridge case is one of the important clues for firearms identification. In this study, a total of 16 features of geometric moments up to the sixth order were extracted from centre of firing pin impression images. A total of five pistols of the Parabellum Vector SPI 9mm model, made in South Africa were used. The pistols were labelled as Pistol A, Pistol B, Pistol C, Pistol D, and Pistol E. A total of 747 bullets have been fired from the five pistols. Under preliminary analysis, Pearson correlation coefficients between all pairs of features showed the features were significant and highly correlated among the features. This problematic features were solved by dividing the features into subgroups of variables based on similar characteristics under principle component analysis. The features that highly correlated were combined into meaningful components or factors. Discriminant analysis was applied to identify the types of pistols used based on the factors obtained. Classification results using cross-validation under discriminant analysis showed that 75.4% of the images were correctly classified according to the pistols used. The results of the study had shown a significant contribution towards Royal Malaysian Police Force in handling crime cases which involve firearms in more systematic manner.

Original languageEnglish
Title of host publicationISCAIE 2012 - 2012 IEEE Symposium on Computer Applications and Industrial Electronics
Pages293-296
Number of pages4
DOIs
Publication statusPublished - 2012
Event2012 IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2012 - Kota Kinabalu
Duration: 3 Dec 20124 Dec 2012

Other

Other2012 IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2012
CityKota Kinabalu
Period3/12/124/12/12

Fingerprint

Crime
Discriminant analysis
Law enforcement

Keywords

  • discriminant analysis
  • firearm identification
  • firing pin impression
  • geometric moment
  • principle component analysis

ASJC Scopus subject areas

  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Ghani, N. A. M., Kamaruddin, S. B. A., Liong, C. Y., & Jemain, A. A. (2012). Firearm identification using numerical features of centre firing pin impression image. In ISCAIE 2012 - 2012 IEEE Symposium on Computer Applications and Industrial Electronics (pp. 293-296). [6482115] https://doi.org/10.1109/ISCAIE.2012.6482115

Firearm identification using numerical features of centre firing pin impression image. / Ghani, Nor Azura Md; Kamaruddin, Saadi Bin Ahmad; Liong, Choong Yeun; Jemain, Abdul Aziz.

ISCAIE 2012 - 2012 IEEE Symposium on Computer Applications and Industrial Electronics. 2012. p. 293-296 6482115.

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

Ghani, NAM, Kamaruddin, SBA, Liong, CY & Jemain, AA 2012, Firearm identification using numerical features of centre firing pin impression image. in ISCAIE 2012 - 2012 IEEE Symposium on Computer Applications and Industrial Electronics., 6482115, pp. 293-296, 2012 IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2012, Kota Kinabalu, 3/12/12. https://doi.org/10.1109/ISCAIE.2012.6482115
Ghani NAM, Kamaruddin SBA, Liong CY, Jemain AA. Firearm identification using numerical features of centre firing pin impression image. In ISCAIE 2012 - 2012 IEEE Symposium on Computer Applications and Industrial Electronics. 2012. p. 293-296. 6482115 https://doi.org/10.1109/ISCAIE.2012.6482115
Ghani, Nor Azura Md ; Kamaruddin, Saadi Bin Ahmad ; Liong, Choong Yeun ; Jemain, Abdul Aziz. / Firearm identification using numerical features of centre firing pin impression image. ISCAIE 2012 - 2012 IEEE Symposium on Computer Applications and Industrial Electronics. 2012. pp. 293-296
@inproceedings{10c2f333e4d447e58820b6b61247d9c5,
title = "Firearm identification using numerical features of centre firing pin impression image",
abstract = "There are many crime cases such as murders or robberies which frequently involve firearms, especially pistols. The centre firing pin impression image on a cartridge case is one of the important clues for firearms identification. In this study, a total of 16 features of geometric moments up to the sixth order were extracted from centre of firing pin impression images. A total of five pistols of the Parabellum Vector SPI 9mm model, made in South Africa were used. The pistols were labelled as Pistol A, Pistol B, Pistol C, Pistol D, and Pistol E. A total of 747 bullets have been fired from the five pistols. Under preliminary analysis, Pearson correlation coefficients between all pairs of features showed the features were significant and highly correlated among the features. This problematic features were solved by dividing the features into subgroups of variables based on similar characteristics under principle component analysis. The features that highly correlated were combined into meaningful components or factors. Discriminant analysis was applied to identify the types of pistols used based on the factors obtained. Classification results using cross-validation under discriminant analysis showed that 75.4{\%} of the images were correctly classified according to the pistols used. The results of the study had shown a significant contribution towards Royal Malaysian Police Force in handling crime cases which involve firearms in more systematic manner.",
keywords = "discriminant analysis, firearm identification, firing pin impression, geometric moment, principle component analysis",
author = "Ghani, {Nor Azura Md} and Kamaruddin, {Saadi Bin Ahmad} and Liong, {Choong Yeun} and Jemain, {Abdul Aziz}",
year = "2012",
doi = "10.1109/ISCAIE.2012.6482115",
language = "English",
isbn = "9781467330329",
pages = "293--296",
booktitle = "ISCAIE 2012 - 2012 IEEE Symposium on Computer Applications and Industrial Electronics",

}

TY - GEN

T1 - Firearm identification using numerical features of centre firing pin impression image

AU - Ghani, Nor Azura Md

AU - Kamaruddin, Saadi Bin Ahmad

AU - Liong, Choong Yeun

AU - Jemain, Abdul Aziz

PY - 2012

Y1 - 2012

N2 - There are many crime cases such as murders or robberies which frequently involve firearms, especially pistols. The centre firing pin impression image on a cartridge case is one of the important clues for firearms identification. In this study, a total of 16 features of geometric moments up to the sixth order were extracted from centre of firing pin impression images. A total of five pistols of the Parabellum Vector SPI 9mm model, made in South Africa were used. The pistols were labelled as Pistol A, Pistol B, Pistol C, Pistol D, and Pistol E. A total of 747 bullets have been fired from the five pistols. Under preliminary analysis, Pearson correlation coefficients between all pairs of features showed the features were significant and highly correlated among the features. This problematic features were solved by dividing the features into subgroups of variables based on similar characteristics under principle component analysis. The features that highly correlated were combined into meaningful components or factors. Discriminant analysis was applied to identify the types of pistols used based on the factors obtained. Classification results using cross-validation under discriminant analysis showed that 75.4% of the images were correctly classified according to the pistols used. The results of the study had shown a significant contribution towards Royal Malaysian Police Force in handling crime cases which involve firearms in more systematic manner.

AB - There are many crime cases such as murders or robberies which frequently involve firearms, especially pistols. The centre firing pin impression image on a cartridge case is one of the important clues for firearms identification. In this study, a total of 16 features of geometric moments up to the sixth order were extracted from centre of firing pin impression images. A total of five pistols of the Parabellum Vector SPI 9mm model, made in South Africa were used. The pistols were labelled as Pistol A, Pistol B, Pistol C, Pistol D, and Pistol E. A total of 747 bullets have been fired from the five pistols. Under preliminary analysis, Pearson correlation coefficients between all pairs of features showed the features were significant and highly correlated among the features. This problematic features were solved by dividing the features into subgroups of variables based on similar characteristics under principle component analysis. The features that highly correlated were combined into meaningful components or factors. Discriminant analysis was applied to identify the types of pistols used based on the factors obtained. Classification results using cross-validation under discriminant analysis showed that 75.4% of the images were correctly classified according to the pistols used. The results of the study had shown a significant contribution towards Royal Malaysian Police Force in handling crime cases which involve firearms in more systematic manner.

KW - discriminant analysis

KW - firearm identification

KW - firing pin impression

KW - geometric moment

KW - principle component analysis

UR - http://www.scopus.com/inward/record.url?scp=84875754627&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875754627&partnerID=8YFLogxK

U2 - 10.1109/ISCAIE.2012.6482115

DO - 10.1109/ISCAIE.2012.6482115

M3 - Conference contribution

SN - 9781467330329

SP - 293

EP - 296

BT - ISCAIE 2012 - 2012 IEEE Symposium on Computer Applications and Industrial Electronics

ER -