Analysis of Geometric Moments as Features for Identification of Forensic Ballistics Specimen.
ABSTRACT Firearm identification is one of the most essential, intricate and demanding tasks in crime investigation. Every firearm,
regardless of its size, make and model, has its own unique ‘fingerprint’ with respect to the marks on fired bullet and cartridge
cases. In this study, we investigate the features extracted from the images of the centre of the cartridge case in which firing
pin impression is located. Geometric moments up to the sixth order were computed to obtain the features based on a total of
747 cartridges case images from five different pistols of the same model. These sixteen features were found to be significantly
different using the MANOVA test. Correlation analysis was used to reduce the dimensionality of the features into only six
features. Classification results using cross-validation show that about 74.0% of the images were correctly classified and
this demonstrates the potential of using moment based features for firearm identification.
- SourceAvailable from: Faouzi Ghorbel[show abstract] [hide abstract]
ABSTRACT: It is well-known that an image can be reconstructed from an infinite set of moments. Many works have focused on the reconstruction aspects of orthogonal moments, and have shown that the image can be reconstructed easily from a finite set of orthogonal moments. However, reconstruction ability of geometric moments is not yet proved. In this paper, the inverse problem of geometric moments is addressed. The approach used consists in recovering the Fourier transform of the image from the geometric moments set. Then, the image is reconstructed using the inverse Fourier transform. Both theoretical and experimental results are given.
Conference Proceeding: Intelligent Imaging of Forensic Ballistics Specimens for ID[show abstract] [hide abstract]
ABSTRACT: The paper describes some of important technologies in the firearm identification using forensic ballistics specimens. The mapping of micro-surfaces on regions on the specimens for comparison to establish identification according to the precision of measurement of the features has been proposed. The physical techniques of linescan, laser depth proofing, and photonic 3D topography can be developed into future tools for forensic ballisticians for identification of cartridge cases and projectiles.Image and Signal Processing, 2008. CISP '08. Congress on; 06/2008