Abstract. 

The article discusses the problem of classification into the categories of “match” and “non-match” for compared images of land impressions on discharged bullets. The aim of the research is to increase the effectiveness of the comparison of images of land impressions by the congruent matching profile segments (CMPS) method. The scientific novelty is in adding to the analysis an additional independent feature, as well as the use of the k-nearest neighbors algorithm at the final stage of traces comparison. The research shows that the accuracy of the classification for the compared pairs of the land impression images by the combined method is about 87%. The work establishes that the analysis of the images by the CMPS method makes it possible to effectively compare images of land impressions with high resolution (less or about 1 μm per pixel). The research is of interest to software developers of automated ballistic identification systems.

Keyworks: 

the congruent matching profile segments method, land impression mark, correlation, classification, k-nearest neighbors algorithm/

PP. 70-82.

DOI 10.14357/20718632210108

 

References

1. A.V. Kokin, K.V. YArmak Sudebnaya ballistika i sudebno-ballisticheskaya ehkspertiza// Uchebnik. Moskva: YUNITI: Zakon i pravo. [Judicial ballistics and forensic ballistic examination // Textbook. Moscow: UNITY: Law] 2015. - 350 p.

2. PCAST. Report to the President - Forensic Science in Criminal Courts: Ensuring Scientific Validity of FeatureComparison Methods. September 2016.

3. Fedorenko V. A., Navrotskaya E. V. Kriterii i algoritm otsenki unikal'nosti kompleksov sovpadayushchikh trass v sledakh na vystrelennykh pulyakh //[Criteria and algorithm for evaluating the uniqueness of complexes of matching tracks in traces on fired bullets // Information Technologies and computing systems], 2019. No. 1. pp. 110-120.

4. Hare, Eric Riemer, "Statistical methods for bullet matching" (2017). Graduate Theses and Dissertations. 15315. https://lib.dr.iastate.edu/etd/15315

5. Banno A. 2004. Estimation of Bullet Striation Similarity Using Neural Networks. Journal of Forensic Sciences. 49(3): 1–5. doi: 10.1520/JFS2002361.

6. Pisantanaroj P., Tanpisuth P., Sinchavanwat P. et al. 2020. Automated Firearm Classification From Bullet Markings Using Deep Learning. IEEE Access. 8: 78236–78251. doi: 10.1109/ACCESS.2020.2989673.

7. Fedorenko V. A., Sorokina K. O. Kompensatsiya iskazheniy izobrazheniy sledov na deformirovannykh pulyakh dlya ikh avtomatizirovannogo sravneniya [Compensation of distortion of images of traces on deformed bullets for their automated comparison. // Sarat. un-ta. New ser. Ser. Economy. Management. Pravo], 2018. Vol.18, vol. 2. S. 227-231. doi: 10.18500/1994-2540-2018-18-2-227-231.

8. Fedorenko V.A. Kolichestvennye kriterii obosnovaniya tozhdestvennosti vtorichnykh sledov na pulyakh, vystrelennykh iz AK-74// Teoriya i praktika sudebnoy ekspertizy/ [Quantitative Identification Criteria for Sec-ondary Toolmarks on Bullets Shot from AK-74// Theory and Practice of Forensic Science] Tom 14, №3 (2019), pp. 54-62.

9. Fedorenko V.A., Ilyasov Yu.V. Primenenie kompleksa «Kondor» v ekspertnykh issledovaniyakh i uchebnom protsesse// Sudebnaya ekspertiza/[Application of the "Condor" complex in the expert research and educational process// Forensic Examination] 2006., №4, P. 60-64.

10. http://www.sbc-spb.com/ (время обращения 11.01.2021)

11. Chen Z., Chu W., Soons J. A., Thompson R. M., Song J., Zhao X. 2019. Fired bullet signature correlation using the Congruent Matching Profile Segments (CMPS) method. Forensic Science International. 305:10-19.

12. Zhe Chen, John Song, Johannes A. Soons, Robert M. Thompson, Xuezeng Zhao. 2020. Pilot study on deformed bullet correlation. Forensic Science International. 306 (2020): 1-11

13. Gonzalez R. C., Woods R. E., Eddins S. L. 2009. Digital Image Processing Using MATLAB. London: Gatesmark Publishing. 827 p.

14. Changmai P., Bora K., Suresh R., Deb N., Mahanta L. B. 2019. On the study of automated identification of firearms through associated striations. 31st International Symposium on Ballistics: Lancaster, PA. doi: 10.12783/ballistics2019/3315615. Brink Kh., Richards D., Feverolf M. Mashinnoe obuchenie. SPb. : Piter, 2017. 336 p.

16. Otkrytyy kurs mashinnogo obucheniya. Tema 3. Klassifikatsiya, derev'ya resheniy i metod blizhayshikh sosedey [Elektronnyy resurs]// Habr: [sayt]. [2017]. URL: https://habr.com/ru/company/ods/blog/322534 (data obrashcheniya: 29.12.2020)

17. Pavel Giverts, Gil Hocherman, Lionel Bokobza and Bernard Schecter. 2013. Interdetermination of Three Micro-scopic Methods for Examination of Striae on Polygonal Bullets. AFTE Journal -- Volume 45 Number 1, pp.48-51.