A Practical Aspect of Identification and Classifying of Guns Based on Gunshot Wound Patterns Using Gene Expression Programming

This paper describes a practical aspect of identification and classifying of Guns based on gunshot wound patterns. We mark a genuinely digitized approach for the characteristic and set of guns used in homicidal cases using Gene expression programming. This approach develops a computationally attractive and effective alternative to investigate the guns used in crime which uses the images of gunshot wound patterns available on the human body. The experimental results achieved for identification and classification accuracy of 91.1 and 93.4%, respectively, on the available database of 30 images including three categories: Hard-contact, Loose-contact and Angled-contact of each pattern consisting of gunshot wounds. Our experimental results from the authentication experiments and false positive identification verses false negative identification also suggest the superiority of the proposed approach over the other popular feature extraction approach considered in this work.