Striation Patterns Classification of Tool Marks Based on Morphological Structure Features

Currently, optical devices, such as microscopes and CCD cameras, are utilized for identification of tool marks in the field of forensic science which mainly depend on the experiences of forensic scientists. Automated identification of tool marks is a challenging task. Its key problems are the representation of tool mark surface and the extraction of tool mark features. A new approach of features extraction for striation patterns is presented. Morphological structure features instead of texture features are extracted from tool marks. The technique is based on the characteristics of the striations on the surface of tool mark with respect to its azimuth, quantity and relations between them. Experimental result shows that the morphological structure features extracted can represent the category of the tool marks.