Izvestiya of Saratov University.

Economics. Management. Law

ISSN 1994-2540 (Print)
ISSN 2542-1956 (Online)

Full text PDF(Ru):
Article type: 

Classifi cation of fi ring pin marks images by weapon specimens using a fully-connected neural network

Fedorenko V. A., Saratov State University
Sorokina Ksenia Olegovna, Saratov State Technical University named after Gagarin Yu. A.
Giverts Pavel Vitalievich, Division of Identification and Forensic Science, National Police HQ

Introduction. The aim of the work is to increase the effi ciency of identifi cation of fi rearms by images of fi ring pin marks in the automatic mode. The relevance of the task is determined by the low effi ciency of the known methods of automatic identifi cation of fi rearm by the fi ring pin marks with individual topological types of individualizing features. This aff ects the investigation of crimes related to the use of fi rearms. Formation of clone images. A training sample was formed; it included 140 original images of fi ring pin marks from 50 classes, on the basis of which about 1000 clone images were made with slightly modifi ed individualizing features. In this case a specifi c specimen of a fi rearm is meant as a class. Neural network training. A fully connected neural network with the following architecture was used as a classifi er: an input layer of neurons; two hidden layers; an output layer. The input layer included 2500 neurons, the fi rst hidden layer was made up of 625 neurons, the second hidden layer contained 156 neurons; the output layer consisted of 50 neurons (in accordance with the number of the classes). Evaluation of the calculation results. The prediction accuracy of the trained neural network was estimated according to the Accuracy metric, which is the ratio of the number of correct predictions to the total number of predictions. The prediction accuracy for the maximum signal on one output neuron was 81%, and when the maximum signals on three output neurons were taken into account, the accuracy was about 91%. Conclusions. The research has shown the possibility of classifi cation of the images of fi ring pin marks by weapons using a fully connected neural network, as well as the eff ectiveness of using artifi cially generated clone images of fi ring pin marks for training a fully connected neural network in cases with a small number of initial objects.

  1. Fedorenko V. A., Kornilov M. V. Assessing similarities fi ring pin traces of fi rearms on their digital images. Informatsionnye Tekhnologii i Vychislitel’nye Sistemy, 2015, no. 3, pp. 92–100 (in Russian).
  2. Song J. Proposed “NIST Ballistics Identifi cation System (NBIS)” Based on 3D Topographic Measurements on Correlation Cells. AFTE Journal, 2013, vol. 45, no. 2, pp. 184–194.
  3. Song J. Proposed “Congruent Matching Cells (CMC)” Method for Ballistic Identifi cation and Error Rate Estimation. AFTE Journal, 2015, vol. 47, no. 3, pp. 177–185.
  4. 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 tekhnologii i vychislitel’nye sistemy [Journal of Information Technologies and Computing Systems], 2019, no. 3, pp. 3–15 (in Russian). https://doi.org/10.14357/20718632190301
  5. Fedorenko V. A., Kornilov M. V. Automatic Comparison of Firing Pin Marks Against Descriptors Independent of Image Orientation. AFTE Journal, 2018, vol. 50, no. 3, pp. 169–175.
  6. Gonzalez R., Woods R. Tsifrovaia obrabotka izobrazhenii [Digital Image Processing]. Moscow, Tecnosphera Publ., 2019. 1104 p. (in Russian).
  7. Furman Ia. A. Vvedenie v konturnyi analiz i ego prilozheniia k obrabotke izobrazhenii i signalov [Contour Analysis Introduction and its Image and Signal Processing Applications]. Moscow, Fizmatlit Publ., 2003. 592 p. (in Russian).
  8. Rashid T. Sozdaem neironnuiu set’ [Make Your Own Neural Network]. St. Petersburg, Alfa-kniga Publ., 2017. 272 p. (in Russian).
  9. 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, Piter Publ., 2018. 480 p. (in Russian)