Analysis of geometric moments as features for firearm identification

Nor Azura Md Ghani, Choong Yeun Liong, Abdul Aziz Jemain

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

The task of identifying firearms from forensic ballistics specimens is exacting in crime investigation since the last two decades. Every firearm, regardless of its size, make and model, has its own unique 'fingerprint'. These fingerprints transfer when a firearm is fired to the fired bullet and cartridge case. The components that are involved in producing these unique characteristics are the firing chamber, breech face, firing pin, ejector, extractor and the rifling of the barrel. These unique characteristics are the critical features in identifying firearms. It allows investigators to decide on which particular firearm that has fired the bullet. Traditionally the comparison of ballistic evidence has been a tedious and time-consuming process requiring highly skilled examiners. Therefore, the main objective of this study is the extraction and identification of suitable features from firing pin impression of cartridge case images for firearm recognition. Some previous studies have shown that firing pin impression of cartridge case is one of the most important characteristics used for identifying an individual firearm. In this study, data are gathered using 747 cartridge case images captured from five different pistols of type 9. mm Parabellum Vektor SP1, made in South Africa. All the images of the cartridge cases are then segmented into three regions, forming three different set of images, i.e. firing pin impression image, centre of firing pin impression image and ring of firing pin impression image. Then geometric moments up to the sixth order were generated from each part of the images to form a set of numerical features. These 48 features were found to be significantly different using the MANOVA test. This high dimension of features is then reduced into only 11 significant features using correlation analysis. Classification results using cross-validation under discriminant analysis show that 96.7% of the images were classified correctly. These results demonstrate the value of geometric moments technique for producing a set of numerical features, based on which the identification of firearms are made.

Original languageEnglish
Pages (from-to)143-149
Number of pages7
JournalForensic Science International
Volume198
Issue number1-3
DOIs
Publication statusPublished - May 2010

Fingerprint

Firearms
Forensic Ballistics
Dermatoglyphics
Discriminant Analysis
Crime
South Africa
Research Personnel

Keywords

  • Correlation analysis
  • Discriminant analysis
  • Feature extraction
  • Firearm identification
  • Geometric moments

ASJC Scopus subject areas

  • Pathology and Forensic Medicine

Cite this

Analysis of geometric moments as features for firearm identification. / Md Ghani, Nor Azura; Liong, Choong Yeun; Jemain, Abdul Aziz.

In: Forensic Science International, Vol. 198, No. 1-3, 05.2010, p. 143-149.

Research output: Contribution to journalArticle

Md Ghani, Nor Azura ; Liong, Choong Yeun ; Jemain, Abdul Aziz. / Analysis of geometric moments as features for firearm identification. In: Forensic Science International. 2010 ; Vol. 198, No. 1-3. pp. 143-149.
@article{925b61595037462d890fbfd0b38cb648,
title = "Analysis of geometric moments as features for firearm identification",
abstract = "The task of identifying firearms from forensic ballistics specimens is exacting in crime investigation since the last two decades. Every firearm, regardless of its size, make and model, has its own unique 'fingerprint'. These fingerprints transfer when a firearm is fired to the fired bullet and cartridge case. The components that are involved in producing these unique characteristics are the firing chamber, breech face, firing pin, ejector, extractor and the rifling of the barrel. These unique characteristics are the critical features in identifying firearms. It allows investigators to decide on which particular firearm that has fired the bullet. Traditionally the comparison of ballistic evidence has been a tedious and time-consuming process requiring highly skilled examiners. Therefore, the main objective of this study is the extraction and identification of suitable features from firing pin impression of cartridge case images for firearm recognition. Some previous studies have shown that firing pin impression of cartridge case is one of the most important characteristics used for identifying an individual firearm. In this study, data are gathered using 747 cartridge case images captured from five different pistols of type 9. mm Parabellum Vektor SP1, made in South Africa. All the images of the cartridge cases are then segmented into three regions, forming three different set of images, i.e. firing pin impression image, centre of firing pin impression image and ring of firing pin impression image. Then geometric moments up to the sixth order were generated from each part of the images to form a set of numerical features. These 48 features were found to be significantly different using the MANOVA test. This high dimension of features is then reduced into only 11 significant features using correlation analysis. Classification results using cross-validation under discriminant analysis show that 96.7{\%} of the images were classified correctly. These results demonstrate the value of geometric moments technique for producing a set of numerical features, based on which the identification of firearms are made.",
keywords = "Correlation analysis, Discriminant analysis, Feature extraction, Firearm identification, Geometric moments",
author = "{Md Ghani}, {Nor Azura} and Liong, {Choong Yeun} and Jemain, {Abdul Aziz}",
year = "2010",
month = "5",
doi = "10.1016/j.forsciint.2010.02.011",
language = "English",
volume = "198",
pages = "143--149",
journal = "Forensic Science International",
issn = "0379-0738",
publisher = "Elsevier Ireland Ltd",
number = "1-3",

}

TY - JOUR

T1 - Analysis of geometric moments as features for firearm identification

AU - Md Ghani, Nor Azura

AU - Liong, Choong Yeun

AU - Jemain, Abdul Aziz

PY - 2010/5

Y1 - 2010/5

N2 - The task of identifying firearms from forensic ballistics specimens is exacting in crime investigation since the last two decades. Every firearm, regardless of its size, make and model, has its own unique 'fingerprint'. These fingerprints transfer when a firearm is fired to the fired bullet and cartridge case. The components that are involved in producing these unique characteristics are the firing chamber, breech face, firing pin, ejector, extractor and the rifling of the barrel. These unique characteristics are the critical features in identifying firearms. It allows investigators to decide on which particular firearm that has fired the bullet. Traditionally the comparison of ballistic evidence has been a tedious and time-consuming process requiring highly skilled examiners. Therefore, the main objective of this study is the extraction and identification of suitable features from firing pin impression of cartridge case images for firearm recognition. Some previous studies have shown that firing pin impression of cartridge case is one of the most important characteristics used for identifying an individual firearm. In this study, data are gathered using 747 cartridge case images captured from five different pistols of type 9. mm Parabellum Vektor SP1, made in South Africa. All the images of the cartridge cases are then segmented into three regions, forming three different set of images, i.e. firing pin impression image, centre of firing pin impression image and ring of firing pin impression image. Then geometric moments up to the sixth order were generated from each part of the images to form a set of numerical features. These 48 features were found to be significantly different using the MANOVA test. This high dimension of features is then reduced into only 11 significant features using correlation analysis. Classification results using cross-validation under discriminant analysis show that 96.7% of the images were classified correctly. These results demonstrate the value of geometric moments technique for producing a set of numerical features, based on which the identification of firearms are made.

AB - The task of identifying firearms from forensic ballistics specimens is exacting in crime investigation since the last two decades. Every firearm, regardless of its size, make and model, has its own unique 'fingerprint'. These fingerprints transfer when a firearm is fired to the fired bullet and cartridge case. The components that are involved in producing these unique characteristics are the firing chamber, breech face, firing pin, ejector, extractor and the rifling of the barrel. These unique characteristics are the critical features in identifying firearms. It allows investigators to decide on which particular firearm that has fired the bullet. Traditionally the comparison of ballistic evidence has been a tedious and time-consuming process requiring highly skilled examiners. Therefore, the main objective of this study is the extraction and identification of suitable features from firing pin impression of cartridge case images for firearm recognition. Some previous studies have shown that firing pin impression of cartridge case is one of the most important characteristics used for identifying an individual firearm. In this study, data are gathered using 747 cartridge case images captured from five different pistols of type 9. mm Parabellum Vektor SP1, made in South Africa. All the images of the cartridge cases are then segmented into three regions, forming three different set of images, i.e. firing pin impression image, centre of firing pin impression image and ring of firing pin impression image. Then geometric moments up to the sixth order were generated from each part of the images to form a set of numerical features. These 48 features were found to be significantly different using the MANOVA test. This high dimension of features is then reduced into only 11 significant features using correlation analysis. Classification results using cross-validation under discriminant analysis show that 96.7% of the images were classified correctly. These results demonstrate the value of geometric moments technique for producing a set of numerical features, based on which the identification of firearms are made.

KW - Correlation analysis

KW - Discriminant analysis

KW - Feature extraction

KW - Firearm identification

KW - Geometric moments

UR - http://www.scopus.com/inward/record.url?scp=77952291754&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952291754&partnerID=8YFLogxK

U2 - 10.1016/j.forsciint.2010.02.011

DO - 10.1016/j.forsciint.2010.02.011

M3 - Article

C2 - 20211535

AN - SCOPUS:77952291754

VL - 198

SP - 143

EP - 149

JO - Forensic Science International

JF - Forensic Science International

SN - 0379-0738

IS - 1-3

ER -