Classification of Tire Tread Images by Using Neural Networks

Image classification represents a complex problem which occurs in variety of science and real life applications. Neural network is one of the excellent tools which could be used to solve this problem. The research presented in this paper is motivated by several consultations with active crime scene investigators. During these consultations, it became apparent, that criminology department is in critical need of advanced software for tire tread print identification. The current software used by crime scene investigators is outdated, time demanding and hard to work with. Application for tire tread print identification should be one of results of project created on the basis of our work with criminology department. This paper presents one of the first steps of this identification - tire tread position identification.