Automatic firearm class identification from cartridge cases

Sridharan Kamalakannan, Christopher J Mann, Philip R. Bingham, Thomas P. Karnowski, Shaun S. Gleason

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

1 Citation (Scopus)

Abstract

We present a machine vision system for automatic identification of the class of firearms by extracting and analyzing two significant properties from spent cartridge cases, namely the Firing Pin Impression (FPI) and the Firing Pin Aperture Outline (FPAO). Within the framework of the proposed machine vision system, a white light interferometer is employed to image the head of the spent cartridge cases. As a first step of the algorithmic procedure, the Primer Surface Area (PSA) is detected using a circular Hough transform. Once the PSA is detected, a customized statistical region-based parametric active contour model is initialized around the center of the PSA and evolved to segment the FPI. Subsequently, the scaled version of the segmented FPI is used to initialize a customized Mumford-Shah based level set model in order to segment the FPAO. Once the shapes of FPI and FPAO are extracted, a shape-based level set method is used in order to compare these extracted shapes to an annotated dataset of FPIs and FPAOs from varied firearm types. A total of 74 cartridge case images non-uniformly distributed over five different firearms are processed using the aforementioned scheme and the promising nature of the results (95% classification accuracy) demonstrate the efficacy of the proposed approach.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Volume7877
DOIs
StatePublished - 2011
Externally publishedYes
EventImage Processing: Machine Vision Applications IV - San Francisco, CA, United States
Duration: Jan 25 2011Jan 27 2011

Other

OtherImage Processing: Machine Vision Applications IV
CountryUnited States
CitySan Francisco, CA
Period1/25/111/27/11

Fingerprint

cartridges
Surface area
Machine Vision
Vision System
Computer vision
primers
Active Contour Model
Hough Transform
Hough transforms
Level Set Method
Parametric Model
apertures
Level Set
Interferometer
Interferometers
computer vision
Efficacy
Demonstrate
Class
interferometers

Keywords

  • Active Contours
  • Firing Pin Aperture
  • Firing Pin Impression
  • Image Segmentation
  • Level Set

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Kamalakannan, S., Mann, C. J., Bingham, P. R., Karnowski, T. P., & Gleason, S. S. (2011). Automatic firearm class identification from cartridge cases. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 7877). [78770P] https://doi.org/10.1117/12.872414

Automatic firearm class identification from cartridge cases. / Kamalakannan, Sridharan; Mann, Christopher J; Bingham, Philip R.; Karnowski, Thomas P.; Gleason, Shaun S.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7877 2011. 78770P.

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

Kamalakannan, S, Mann, CJ, Bingham, PR, Karnowski, TP & Gleason, SS 2011, Automatic firearm class identification from cartridge cases. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 7877, 78770P, Image Processing: Machine Vision Applications IV, San Francisco, CA, United States, 1/25/11. https://doi.org/10.1117/12.872414
Kamalakannan S, Mann CJ, Bingham PR, Karnowski TP, Gleason SS. Automatic firearm class identification from cartridge cases. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7877. 2011. 78770P https://doi.org/10.1117/12.872414
Kamalakannan, Sridharan ; Mann, Christopher J ; Bingham, Philip R. ; Karnowski, Thomas P. ; Gleason, Shaun S. / Automatic firearm class identification from cartridge cases. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 7877 2011.
@inproceedings{c2a200d53c6645fcb37501545918df0a,
title = "Automatic firearm class identification from cartridge cases",
abstract = "We present a machine vision system for automatic identification of the class of firearms by extracting and analyzing two significant properties from spent cartridge cases, namely the Firing Pin Impression (FPI) and the Firing Pin Aperture Outline (FPAO). Within the framework of the proposed machine vision system, a white light interferometer is employed to image the head of the spent cartridge cases. As a first step of the algorithmic procedure, the Primer Surface Area (PSA) is detected using a circular Hough transform. Once the PSA is detected, a customized statistical region-based parametric active contour model is initialized around the center of the PSA and evolved to segment the FPI. Subsequently, the scaled version of the segmented FPI is used to initialize a customized Mumford-Shah based level set model in order to segment the FPAO. Once the shapes of FPI and FPAO are extracted, a shape-based level set method is used in order to compare these extracted shapes to an annotated dataset of FPIs and FPAOs from varied firearm types. A total of 74 cartridge case images non-uniformly distributed over five different firearms are processed using the aforementioned scheme and the promising nature of the results (95{\%} classification accuracy) demonstrate the efficacy of the proposed approach.",
keywords = "Active Contours, Firing Pin Aperture, Firing Pin Impression, Image Segmentation, Level Set",
author = "Sridharan Kamalakannan and Mann, {Christopher J} and Bingham, {Philip R.} and Karnowski, {Thomas P.} and Gleason, {Shaun S.}",
year = "2011",
doi = "10.1117/12.872414",
language = "English (US)",
isbn = "9780819484147",
volume = "7877",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

TY - GEN

T1 - Automatic firearm class identification from cartridge cases

AU - Kamalakannan, Sridharan

AU - Mann, Christopher J

AU - Bingham, Philip R.

AU - Karnowski, Thomas P.

AU - Gleason, Shaun S.

PY - 2011

Y1 - 2011

N2 - We present a machine vision system for automatic identification of the class of firearms by extracting and analyzing two significant properties from spent cartridge cases, namely the Firing Pin Impression (FPI) and the Firing Pin Aperture Outline (FPAO). Within the framework of the proposed machine vision system, a white light interferometer is employed to image the head of the spent cartridge cases. As a first step of the algorithmic procedure, the Primer Surface Area (PSA) is detected using a circular Hough transform. Once the PSA is detected, a customized statistical region-based parametric active contour model is initialized around the center of the PSA and evolved to segment the FPI. Subsequently, the scaled version of the segmented FPI is used to initialize a customized Mumford-Shah based level set model in order to segment the FPAO. Once the shapes of FPI and FPAO are extracted, a shape-based level set method is used in order to compare these extracted shapes to an annotated dataset of FPIs and FPAOs from varied firearm types. A total of 74 cartridge case images non-uniformly distributed over five different firearms are processed using the aforementioned scheme and the promising nature of the results (95% classification accuracy) demonstrate the efficacy of the proposed approach.

AB - We present a machine vision system for automatic identification of the class of firearms by extracting and analyzing two significant properties from spent cartridge cases, namely the Firing Pin Impression (FPI) and the Firing Pin Aperture Outline (FPAO). Within the framework of the proposed machine vision system, a white light interferometer is employed to image the head of the spent cartridge cases. As a first step of the algorithmic procedure, the Primer Surface Area (PSA) is detected using a circular Hough transform. Once the PSA is detected, a customized statistical region-based parametric active contour model is initialized around the center of the PSA and evolved to segment the FPI. Subsequently, the scaled version of the segmented FPI is used to initialize a customized Mumford-Shah based level set model in order to segment the FPAO. Once the shapes of FPI and FPAO are extracted, a shape-based level set method is used in order to compare these extracted shapes to an annotated dataset of FPIs and FPAOs from varied firearm types. A total of 74 cartridge case images non-uniformly distributed over five different firearms are processed using the aforementioned scheme and the promising nature of the results (95% classification accuracy) demonstrate the efficacy of the proposed approach.

KW - Active Contours

KW - Firing Pin Aperture

KW - Firing Pin Impression

KW - Image Segmentation

KW - Level Set

UR - http://www.scopus.com/inward/record.url?scp=79953128736&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79953128736&partnerID=8YFLogxK

U2 - 10.1117/12.872414

DO - 10.1117/12.872414

M3 - Conference contribution

SN - 9780819484147

VL - 7877

BT - Proceedings of SPIE - The International Society for Optical Engineering

ER -