The rise in crimes and the use of firearms necessitate ballistic and forensic science laboratories worldwide to come up with quick and accurate solutions. The identification process of firearms is a complex yet very sensitive and vital step in evidence examination in the process of crime investigation. The use of modern techniques like image processing and pattern recognition can contribute to increase the accuracy as well as reduce the time in the process of identification. Manually, many features of a spent bullet of a firearm are investigated for this purpose, striations being an important one of them. The aim of the study is to automatically segment out the striations present in a fired bullet through image processing and segmentation techniques, which is a real challenge as these marks are very fine. For the study, images of two fired bullets of .22 in. caliber rimfire cartridge, fired from one and the same firearm (semi-automatic pistol) were considered for the preliminary study. Experimental results show that proposed techniques can be efficiently used for firearm identification through digitizing and analyzing the fired bullets specimens. The visual comparison reveals that the Fuzzy C Means technique gives the clearest segmented result of the striations. This could be of great use in the future as it is a time-saving process. This can be of great help in feature identification, vis-à-vis manual searching of the feature under a comparison microscope for identification of the firearm.

Ballistic, Firearm identification, Striations, Segmentation

[1] Li, D. G., “Image processing for the positive identification of forensic ballistics specimens”, In Proceedings of Sixth International Conference of Information Fusion, Australia, pp. 1494-1498, 2003.
[2] Nigam, R. K., Waghmare N.P., Gupta A. K., “Evaluation and analysis of different type of edge detection techniques on cartridge case image”, International Journal on Recent and Innovation Trends in Computing and Communication, Vol. 2, pp, 3258–3261, 2014.
[3] Nigam, R. K., Waghmare N.P., Gupta A. K., “Digital Enhancement of Bullet Striation Mark by Image Processing Techniques”, International Journal of Advance Research in Computer Science and Management Studies. Vol. 2(12), 340-345, 2014.
[4] Suresh, R., “A simple method to compare firing pin marks using stereomicroscope and Microsoft office (Windows 8) tools”, Forensic Science International, Vol. 277, pp. e1-e10, 2017.
[5] Smith, C.L., “An intelligent imaging approach to the identification of forensic ballistics specimens”, In Proceedings ICII, Beijing International Conferences. Vol. 3, pp. 390–396, 2002.
[6] Ingale, P. M., "The importance of Digital Image Processing and its applications", International Journal of Scientific Research in Computer Science and Engineering, Vol.6, Issue.1, pp.31-32, 2018.
[7] Umorya, P., and Singh, R., "A Comparative Based Review on Image Segmentation of Medical Image and its Technique", International Journal of Scientific Research in Computer Science and Engineering, Vol.5, Issue.2, pp.71-76, 2017.
[8] Bijhold, J. and Geradts, Z., “Overview of Pattern recognition and image processing in forensic science”, Anil Aggrawal’s Internet Journal of Forensic Medicine and Toxicology, Vol. 1, 2000.
[9] Geradts, Z., Bijhold, J. and Hermsen, R., “Image matching algorithms for breech face marks and firing pins in a database of spent cartridge cases of firearms”, Forensic Science International, Vol. 119, pp. 97-106, 2001.
[10] Rosiak, J., “Automated Systems of Ballistic Identification”, In 13th INTERPOL Forensic Science Symposium, Lyon, France, 2000.
[11] Mazumdar, D., Mitra, S. and Kar, A., “An Automatic Bullet Cartridge Identification System”, In The 5th Asian Conference on Computer Vision, Melbourne, Australia, pp. 1-6, 2002.
[12] Li, D., “Ballistics Image Processing and Analysis for Firearm Identification”, Image processing, IEEE Transactions on, Vol. 15, pp. 2857 – 2865, 2006.
[13] Xie. F., Xiao, S., Blunt, L., Zeng, W., Jiang, X., “Automated bullet-identification system based on surface topography techniques”, Wear, 266, pp. 518–522, 2009.
[14] Gerules, G., Bhatia, S. K., Jackson, D. E., “A survey of image processing techniques and statistics for ballistic specimens in forensic science”, Science and Justice, 53, pp. 236–250, 2013.
[15] Geradts, Z., Bijhold, J. and Hermsen, R., “Use of Correlation algorithms in a database of spent cartridge cases of firearms”, In 13th Interpol Forensic Science Symposium, Lyon, France, 1998.
[16] Saferstein, “Firearms, Tool Marks, and Other Impressions, Forensic Science: An Introduction”, Prentice Hall, Chapter 15 1995.
[17] Gonzalez, R. C., Woods, R. E., “Digital Image Processing”, 2nd Edition., Publishing House of Electronics Industry, 2007.
[18] Madasu, V. K., and Yarlagadda, P., “An in-depth comparison of four texture segmentation methods”, 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007), Glenelg, Australia, pp. 366-372, 2007.
[19] Chankong, T., Theera-Umpon, N., Auephanwiriyakul, S., “Automatic cervical cell segmentation and classification in Pap smears”, Computer methods and programs in biomedicine, Vol. 113, pp. 539–556, 2014.
[20] A. Banno, T. Masuda, K. Ikeuchi, Forensic Retrieval of Striations on Fired Bullets by using 3D Geometric Data, MVA2005 IAPR Conference on Machine Vision Applications, Tsukuba Science City, Japan, (2005) 214-217.