Features extraction and classification of cartridge images for ballistics identification
IEA/AIE'10 Proceedings of the 23rd international conference on Industrial engineering and other applications of applied intelligent systems - Volume Part III
Proceedings of the on Multimedia and security
Forensic ballistic analysis using a 3D sensor device
Proceedings of the on Multimedia and security
Open set source camera attribution and device linking
Pattern Recognition Letters
| Hi-index | 0.01 |
This paper is based upon the observation that, when a bullet is fired, it creates characteristic markings on the cartridge case and projectile. From these markings, over 30 different features can be distinguished, which, in combination, produce a "fingerprint" for a firearm. By analyzing features within such a set of firearm fingerprints, it will be possible to identify not only the type and model of a firearm, but also each and every individual weapon just as effectively as human fingerprint identification. A new analytic system based on the fast Fourier transform for identifying projectile specimens by the line-scan imaging technique is proposed in this paper. This paper develops optical, photonic, and mechanical techniques to map the topography of the surfaces of forensic projectiles for the purpose of identification. Experiments discussed in this paper are performed on images acquired from 16 various weapons. Experimental results show that the proposed system can be used for firearm identification efficiently and precisely through digitizing and analyzing the fired projectiles specimens