A robust firearm identification algorithm of forensic ballistics specimens

Z. L. Chuan, Abdul Aziz Jemain, Choong Yeun Liong, N. A.M. Ghani, L. K. Tan

Research output: Contribution to journalArticle

Abstract

There are several inherent difficulties in the existing firearm identification algorithms, include requiring the physical interpretation and time consuming. Therefore, the aim of this study is to propose a robust algorithm for a firearm identification based on extracting a set of informative features from the segmented region of interest (ROI) using the simulated noisy center-firing pin impression images. The proposed algorithm comprises Laplacian sharpening filter, clustering-based threshold selection, unweighted least square estimator, and segment a square ROI from the noisy images. A total of 250 simulated noisy images collected from five different pistols of the same make, model and caliber are used to evaluate the robustness of the proposed algorithm. This study found that the proposed algorithm is able to perform the identical task on the noisy images with noise levels as high as 70%, while maintaining a firearm identification accuracy rate of over 90%.

Original languageEnglish
Article number012126
JournalJournal of Physics: Conference Series
Volume890
Issue number1
DOIs
Publication statusPublished - 21 Sep 2017

Fingerprint

ballistics
estimators
filters
thresholds

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Cite this

A robust firearm identification algorithm of forensic ballistics specimens. / Chuan, Z. L.; Jemain, Abdul Aziz; Liong, Choong Yeun; Ghani, N. A.M.; Tan, L. K.

In: Journal of Physics: Conference Series, Vol. 890, No. 1, 012126, 21.09.2017.

Research output: Contribution to journalArticle

@article{6bd1c4549154430481c877bf3bd527bb,
title = "A robust firearm identification algorithm of forensic ballistics specimens",
abstract = "There are several inherent difficulties in the existing firearm identification algorithms, include requiring the physical interpretation and time consuming. Therefore, the aim of this study is to propose a robust algorithm for a firearm identification based on extracting a set of informative features from the segmented region of interest (ROI) using the simulated noisy center-firing pin impression images. The proposed algorithm comprises Laplacian sharpening filter, clustering-based threshold selection, unweighted least square estimator, and segment a square ROI from the noisy images. A total of 250 simulated noisy images collected from five different pistols of the same make, model and caliber are used to evaluate the robustness of the proposed algorithm. This study found that the proposed algorithm is able to perform the identical task on the noisy images with noise levels as high as 70{\%}, while maintaining a firearm identification accuracy rate of over 90{\%}.",
author = "Chuan, {Z. L.} and Jemain, {Abdul Aziz} and Liong, {Choong Yeun} and Ghani, {N. A.M.} and Tan, {L. K.}",
year = "2017",
month = "9",
day = "21",
doi = "10.1088/1742-6596/890/1/012126",
language = "English",
volume = "890",
journal = "Journal of Physics: Conference Series",
issn = "1742-6588",
publisher = "IOP Publishing Ltd.",
number = "1",

}

TY - JOUR

T1 - A robust firearm identification algorithm of forensic ballistics specimens

AU - Chuan, Z. L.

AU - Jemain, Abdul Aziz

AU - Liong, Choong Yeun

AU - Ghani, N. A.M.

AU - Tan, L. K.

PY - 2017/9/21

Y1 - 2017/9/21

N2 - There are several inherent difficulties in the existing firearm identification algorithms, include requiring the physical interpretation and time consuming. Therefore, the aim of this study is to propose a robust algorithm for a firearm identification based on extracting a set of informative features from the segmented region of interest (ROI) using the simulated noisy center-firing pin impression images. The proposed algorithm comprises Laplacian sharpening filter, clustering-based threshold selection, unweighted least square estimator, and segment a square ROI from the noisy images. A total of 250 simulated noisy images collected from five different pistols of the same make, model and caliber are used to evaluate the robustness of the proposed algorithm. This study found that the proposed algorithm is able to perform the identical task on the noisy images with noise levels as high as 70%, while maintaining a firearm identification accuracy rate of over 90%.

AB - There are several inherent difficulties in the existing firearm identification algorithms, include requiring the physical interpretation and time consuming. Therefore, the aim of this study is to propose a robust algorithm for a firearm identification based on extracting a set of informative features from the segmented region of interest (ROI) using the simulated noisy center-firing pin impression images. The proposed algorithm comprises Laplacian sharpening filter, clustering-based threshold selection, unweighted least square estimator, and segment a square ROI from the noisy images. A total of 250 simulated noisy images collected from five different pistols of the same make, model and caliber are used to evaluate the robustness of the proposed algorithm. This study found that the proposed algorithm is able to perform the identical task on the noisy images with noise levels as high as 70%, while maintaining a firearm identification accuracy rate of over 90%.

UR - http://www.scopus.com/inward/record.url?scp=85030705561&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030705561&partnerID=8YFLogxK

U2 - 10.1088/1742-6596/890/1/012126

DO - 10.1088/1742-6596/890/1/012126

M3 - Article

VL - 890

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

SN - 1742-6588

IS - 1

M1 - 012126

ER -