Artificial neural network implementation on firearm recognition system with respect to ring firing pin impression image

Artificial neural network implementation on firearm recognition system with respect to ring firing pin impression image

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 befor...

Full description

Bibliographic Details
Main Authors: Ahmad Kamaruddin, Saadi, Md Ghani, Nor Azura, Liong, Choong-Yeun, Jemain, Abdul Aziz
Format: Conference or Workshop Item
Language:English
Published: Journal Sains dan Matematik UPSI 2011
Subjects:
QA75 Electronic computers. Computer science
Online Access:http://irep.iium.edu.my/16163/
http://irep.iium.edu.my/16163/
http://irep.iium.edu.my/16163/1/KOLUPSI.pdf
id iium-16163
recordtype eprints
spelling iium-161632017-06-19T02:10:08Z http://irep.iium.edu.my/16163/ Artificial neural network implementation on firearm recognition system with respect to ring firing pin impression image Ahmad Kamaruddin, Saadi Md Ghani, Nor Azura Liong, Choong-Yeun Jemain, Abdul Aziz QA75 Electronic computers. Computer science 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 ring image computed from a total of 747 cartridge case images. Under pattern recognition theory, the supervised features of ring 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/sigmoid transfer functions with ‘trainscg’ algorithm was found to yield the best classification result using cross-validation, where 98% 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 ring firing pin impression with high precision and fast classification results. Journal Sains dan Matematik UPSI 2011-10-06 Conference or Workshop Item NonPeerReviewed application/pdf en http://irep.iium.edu.my/16163/1/KOLUPSI.pdf Ahmad Kamaruddin, Saadi and Md Ghani, Nor Azura and Liong, Choong-Yeun and Jemain, Abdul Aziz (2011) Artificial neural network implementation on firearm recognition system with respect to ring firing pin impression image. In: Kolokium Kebangsaan Pasca Siswazah Sains dan Matematik 2011, 1 Oktober 2011, Dewan Konvensyen, Bangunan E-Learning, UPSI. (Unpublished) http://fsmt.upsi.edu.my/kolupsi2011/index.php?option=com_content&view=article&id=15&Itemid=15
repository_type Digital Repository
institution_category Local University
institution International Islamic University Malaysia
building IIUM Repository
collection Online Access
language English
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Ahmad Kamaruddin, Saadi
Md Ghani, Nor Azura
Liong, Choong-Yeun
Jemain, Abdul Aziz
Artificial neural network implementation on firearm recognition system with respect to ring firing pin impression image
description 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 ring image computed from a total of 747 cartridge case images. Under pattern recognition theory, the supervised features of ring 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/sigmoid transfer functions with ‘trainscg’ algorithm was found to yield the best classification result using cross-validation, where 98% 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 ring firing pin impression with high precision and fast classification results.
format Conference or Workshop Item
author Ahmad Kamaruddin, Saadi
Md Ghani, Nor Azura
Liong, Choong-Yeun
Jemain, Abdul Aziz
author_facet Ahmad Kamaruddin, Saadi
Md Ghani, Nor Azura
Liong, Choong-Yeun
Jemain, Abdul Aziz
author_sort Ahmad Kamaruddin, Saadi
title Artificial neural network implementation on firearm recognition system with respect to ring firing pin impression image
title_short Artificial neural network implementation on firearm recognition system with respect to ring firing pin impression image
title_full Artificial neural network implementation on firearm recognition system with respect to ring firing pin impression image
title_fullStr Artificial neural network implementation on firearm recognition system with respect to ring firing pin impression image
title_full_unstemmed Artificial neural network implementation on firearm recognition system with respect to ring firing pin impression image
title_sort artificial neural network implementation on firearm recognition system with respect to ring firing pin impression image
publisher Journal Sains dan Matematik UPSI
publishDate 2011
url http://irep.iium.edu.my/16163/
http://irep.iium.edu.my/16163/
http://irep.iium.edu.my/16163/1/KOLUPSI.pdf
first_indexed 2023-09-18T20:25:01Z
last_indexed 2023-09-18T20:25:01Z
_version_ 1777408359105822720

Similar Items