 |
V. A. Fedorenko, K. O. Sorokina, P. V. Giverts Multigroup classification of Firing Pin Marks with the use of a Fully Connected Neural Network |
 |
|
Abstract.
The article discusses the problem of classifying the images of firing pin marks using a fully connected neural network. The purpose of this work was to study the effectiveness of using clone images of firing pin marks with modified features in order to improve the quality of training of fully connected neural networks, as well as to evaluate the accuracy of multigroup classification of firing pin marks made by different weapons using this type of network. The scientific novelty of the work is the formation of clone images of firing pin marks in order to increase the number of objects in the training sample and to artificially increase the feature diversity of objects of each class. The conducted studies have shown that the classification accuracy of the analyzed objects reaches approximately 84% in the case of a fixed value of the classifying criterion and 94-98% when classified according to the three largest signals on the output neurons. The work is of interest to developers of software for automated ballistic identification systems.
Keywords:
firing pin marks, fully connected neural networks, multigroup classification, sampling augmentation.
PP. 43-57.
DOI 10.14357/20718632220305 References
1. Fedorenko V.A. Kornilov M.V. 2015. Ocenka skhozhesti sledov bojkov ognestrel’nogo oruzhya po ih cifrovim izobrageniyam [Assessing similarities firing pin traces of firearms on their digital images]. Informacionnye technologii I vychislitel’nye sistemy [Information yechnology and computing systems]. 3:92-100. 2. Fedorenko V.A., Gvozdkov S.N., Grabovec E.E. 2018. Vliyanie neodnorodnostej poverhnosti kapsyuley na variativnost’ staticheskih sledov bojkov [Influence of Inhomogeneities of the Surface of Caps on Variability of Static Firing Pin Traces]. Izv. Saratov Univ. (N.S.), Ser. Economics. Management. Law. 18.(2):202-207. 3. Song J. 2013. Proposed “NIST Ballistics Identification System (NBIS)” Based on 3D Topographic Measurements on Correlation Cells. AFTE Journal. 45(2), p.184-194. 4. John Song, Proposed “Congruent Matching Cells (CMC)” Method for Ballistic Identification and Error Rate Estimation// AFTE 2015, Vol.47, №3, pp.177-185. 5. Sorokina K.O., Fedorenko V.A., Giverts P.V. Evaluation of the Similarity of Images of Breech Face Marks Using the Method of Correlation Cells. Informatsionnye technologii I vychislitel’nye sistemy [Information Technologies and Computing Systems], 2019, no. 3, pp. 3-15. DOI: 10.14357/20718632190301 (in Russian). 6. Bailey, Ken (1994). "Numerical Taxonomy and Cluster Analysis". Typologies and Taxonomies. p. 34. ISBN 9780803952591. 7. Kornilov M., Fedorenko V. Use of the Cluster Analysis to compare the Digital Images Traces of the Firing Pin// Proceedings of Saratov University 2014. Vol. 14. Ser. Economic. Management. Law, iss.1. P.2., pp 187-190. 8. Fedorenko V.A., Kornilov M.V. Automatic Comparison of Firing Pin Marks Against Descriptors Independent of Image Orientation // AFTE 2018, pp. 169-175. 9. Gonzalez R., Woods R. Tsifrovaia obrabotka izobrazhenii [Digital Image Processing]. Moscow, JSC "Tecnosphera", 2019. 1104 p. (in Russian). 10. Furman Ia. A. Vvedenie v konturnyi analiz i ego prilozhe-niia k obrabotke izobrazhenii i signalov [Contour Analysis Introduction and its Image and Signal Processing Applications]. Moscow, Physics and mathematics publishers, 2003. 592 p. (in Russian). 11. S.B.A. Kamaruddin, N.A.M. Ghani, C.-Y. Liong, A.A. Jemain, Firearm Classification using Neural Networks on Ring of Firing Pin Impression Images, Adv. Distrib. Comput. Artif. Intell. J. 1 (2012) 27–35. https://doi.org/10.14201/ADCAIJ20121312734 12. O. Giudice, L. Guarnera, A.B. Paratore, G.M. Farinella, S. Battiato, Siamese Ballistics Neural Network, in: 2019 IEEE Int. Conf. Image Process., IEEE, 2019: pp. 4045–4049. https://doi.org/10.1109/ICIP.2019.8803619 13. Rashid T. Sozdaem neironnuiu set' [Make your own neural network]. St. Petersburg, Alfa-Book LLC, 2017. 272 p. (in Russian). 14. Nikolenko S. I., Kadurin A. A., Arkhangel'skaia E. O. Glubokoe obuchenie. Pogruzhenie v mir neironnykh setei [Deep Learning. Dipping into the world of neural networks]. St. Petersburg, Petersburg, 2018. 480 p. (in Russian). 2. David A. Forsyth, Jean Ponce “Computer Vision. A Modern Approach” 2018, p. 960.
|
