Abstract
The identification of the firearm model that triggered the firing of a bullet is an important forensic information that, historically, has been done by trained examiners through visual inspection using microscopes. This is an extensive and very time-consuming process that requires the examiners to be trained to identify and compare the fired cartridges. This paper proposes an automated objective method for binary classifying pairs of fired cartridge head images as belonging to the same or different classes, using siamese neural networks (SNNs). With this technique, an accuracy of up to 70% was reached by using firing pin mark images as the input of the SNN. For the training and optimization of the network this paper also analyses and presents different image preprocessing approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zheng, X., Soons, J., Vorburger, T., Song, J., Renegar, T., Thompson, R.: Applications of surface metrology in firearm identification 2, 014012 (2014)
Md Ghani, N.A., Liong, C.-Y., Jemain, A.A.: Analysis of geometric moments as features for firearm identification 198(1), 143–149 (2010)
Gerules, G., Bhatia, S.K., Jackson, D.E.: A survey of image processing techniques and statistics for ballistic specimens in forensic science 53(2), 236–250 (2013)
Huang, Z., Leng, J.: A novel binarization algorithm for ballistics imaging systems, volume 3. Journal Abbreviation: Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010 Pages: 1291 Publication Title: Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP (2010)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)
Chow, C.K., Kaneko, T.: Automatic boundary detection of the left ventricle from cineangiograms 5(4), 388–410 (1972)
Yanowitz, S.D., Bruckstein, A.M.: A new method for image segmentation 46(1), 82–95 (1989)
Leng, J., Huang, Z.: On analysis of circle moments and texture features for cartridge images recognition 39(2), 2092–2101 (2012)
Kamaruddin, S.B.A., Md Ghani, S.B.A., Liong, C.-Y., Jemain, A.A.: Firearm recognition based on whole firing pin impression image via backpropagation neural network. In: 2011 International Conference on Pattern Analysis and Intelligence Robotics, vol. 1, pp. 177–182 (2011)
Giudice, O., Guarnera, L., Paratore, A.B., Farinella, G.M., Battiato, S.: Siamese ballistics neural network. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 4045–4049 (2019). ISSN: 2381-8549
“Toolscan” Forensic.cz (Laboratory Imaging s.r.o.). https://www.forensic.cz/en/products/toolscan. Accessed 23 Oct 2021
Koch, G.R.: Siamese neural networks for one-shot image recognition (2015)
“keras documentation” Team Keras. https://keras.io/keras_tuner/. Accessed 24 Oct 2021
Acknowledgments
Sérgio Valentim received support from the Portuguese National Funds through SAMA 2020 program in collaboration with the Portuguese Criminal Police.
Funding
This research was funded by the Foundation for Science and Technology (FCT) through ISTAR-IUL’s project UIDB/04466/2020 and UIDP/04466/2020.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Valentim, S., Fonseca, T., Ferreira, J., Brandão, T., Ribeiro, R., Nae, S. (2022). Gun Model Classification Based on Fired Cartridge Case Head Images with Siamese Networks. In: Abraham, A., Gandhi, N., Hanne, T., Hong, TP., Nogueira Rios, T., Ding, W. (eds) Intelligent Systems Design and Applications. ISDA 2021. Lecture Notes in Networks and Systems, vol 418. Springer, Cham. https://doi.org/10.1007/978-3-030-96308-8_119
Download citation
DOI: https://doi.org/10.1007/978-3-030-96308-8_119
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96307-1
Online ISBN: 978-3-030-96308-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)