Neural Network in Object Classification Using Matlab

Presented paper deals with images of nanotubes that provide a new way of a surface bioactivation of dental titanium implants. The evaluation of selected material parameters forms an important part of material quality assessment. The first step is an image segmentation and object detection. In the following step, object classification is a crucial point in separation object. Various methods could be used for classification implementation, neural network provides one of them. In the paper, an object classification method based on competitive neural network use is presented. In the first part, basic principles of neural network are described. In the next part, selected classification method is tested on a set of images.