Towards automated firearm identification based on high resolution 3D data: rotation-invariant features for multiple line-profile-measurement of firing pin shapes

Understanding and evaluation of potential evidence, as well as evaluation of automated systems for forensic examinations currently play an important role within the domain of digital crime scene analysis. The application of 3D sensing and pattern recognition systems for automatic extraction and comparison of firearm related tool marks is an evolving field of research within this domain. In this context, the design and evaluation of rotation-invariant features for use on topography data play a particular important role. In this work, we propose and evaluate a 3D imaging system along with two novel features based on topography data and multiple profile-measurement-lines for automatic matching of firing pin shapes. Our test set contains 72 cartridges of three manufactures shot by six different 9mm guns. The entire pattern recognition workflow is addressed. This includes the application of confocal microscopy for data acquisition, preprocessing covers outlier handling, data normalization, as well as necessary segmentation and registration. Feature extraction involves the two introduced features for automatic comparison and matching of 3D firing pin shapes. The introduced features are called ‘Multiple-Circle-Path’ (MCP) and ‘Multiple-Angle-Path’ (MAP). Basically both features are compositions of freely configurable amounts of circular or straight path-lines combined with statistical evaluations. During the first part of evaluation (E1), we examine how well it is possible to differentiate between two 9mm weapons of the same mark and model. During second part (E2), we evaluate the discrimination accuracy regarding the set of six different 9mm guns. During the third part (E3), we evaluate the performance of the features in consideration of different rotation angles. In terms of E1, the best correct classification rate is 100% and in terms of E2 the best result is 86%. The preliminary results for E3 indicate robustness of both features regarding rotation. However, in future work these results have to be validated using an enlarged test set.

[1]  P. Thumwarin,et al.  Firearm identification based on rotation invariant feature of cartridge case , 2008, 2008 SICE Annual Conference.

[2]  Jinsong Leng,et al.  Features Extraction and Classification of Cartridge Images for Ballistics Identification , 2010, IEA/AIE.

[3]  Saadi Bin Ahmad Kamaruddin,et al.  Firearm recognition based on whole firing pin impression image via backpropagation neural network , 2011, 2011 International Conference on Pattern Analysis and Intelligence Robotics.

[4]  Ufuk Sakarya,et al.  Three-dimensional surface reconstruction for cartridge cases using photometric stereo. , 2008, Forensic science international.

[5]  Piyamas Suapang,et al.  Tool and Firearm Identification System Based on Image Processing , 2011, 2011 11th International Conference on Control, Automation and Systems.

[6]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[7]  Michael Hill,et al.  Document Title: Consecutive and Random Manufactured Semi- Automatic Pistol Breech Face and Fired Cartridge Case Evaluations , 2014 .

[8]  Abdul Aziz Jemain,et al.  Classification of pistol via numerical based features of firing pin impression image , 2013, 2013 IEEE Symposium on Computers & Informatics (ISCI).

[9]  Max Robinson,et al.  Line-scan imaging for the positive identification of ballistics specimens , 2000, Proceedings IEEE 34th Annual 2000 International Carnahan Conference on Security Technology (Cat. No.00CH37083).

[10]  Dongguang Li.  Ballistics Projectile Image Analysis for Firearm Identification , 2006, IEEE Transactions on Image Processing.

[11]  Rachel Bolton-King,et al.  What are the Prospects of 3D Profiling Systems Applied to Firearms and Toolmark Identification , 2010 .

[12]  C.L. Smith.  Profiling Toolmarks on Forensic Ballistics Specimens: An Experimental Approach , 2006, Proceedings 40th Annual 2006 International Carnahan Conference on Security Technology.

[13]  Claus Vielhauer,et al.  Digital crime scene analysis: automatic matching of firing pin impressions on cartridge bottoms using 2d and 3d spatial features , 2014, IH&MMSec '14.

[14]  Benjamin Bachrach,et al.  Development of a 3D-based automated firearms evidence comparison system. , 2002, Journal of forensic sciences.

[15]  J Bijhold,et al.  Image matching algorithms for breech face marks and firing pins in a database of spent cartridge cases of firearms. , 2001, Forensic science international.

[16]  Jinsong Leng,et al.  On analysis of circle moments and texture features for cartridge images recognition , 2012, Expert Syst. Appl..

[17]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[18]  Dongguang Li.  A New Approach for Firearm Identification with Hierarchical Neural Networks Based on Cartridge Case Images , 2006, 2006 5th IEEE International Conference on Cognitive Informatics.

[19]  P. Thumwarin.  An Automatic System for Firearm Identification , 2008, 2008 International Symposium on Communications and Information Technologies.

[20]  Claus Vielhauer,et al.  Forensic ballistic analysis using a 3D sensor device , 2012, MM&Sec '12.

[21]  Abdul Aziz Jemain,et al.  Analysis of geometric moments as features for firearm identification. , 2010, Forensic science international.

[22]  Choong-Yeun Liong,et al.  Firearm identification using numerical features of centre firing pin impression image , 2012, 2012 International Symposium on Computer Applications and Industrial Electronics (ISCAIE).