FISOFM: firearms identification based on SOFM model of neural network

Abstract

Firearms identification (FI) has been becoming a serious and increasing part of crime investigation for the last two decades. We propose a solution to FI using Neural Network (NN) technology. Lots of methods have been using in FI such as extractor mark, breach mark, ejector mark, and chambering mark identification, etc. We choose the chambering mark identification as our method in this research. It is a simple and useful method for crime investigation. Because of the principle of tool mark, we may identify the firearms. The chambering mark needs to be scanned, preprocessed, segmented, described, reduced and enhanced, and will be recognized by its individual characteristic via the Self-Organizing Feature Map(SOFM) model of NN. It will ease the burden of forensic laboratory's because they do not need to identify the tool mark via microscope.<>