Comparative Analysis and Classification of Features for Image Models

This study has been conducted in the framework of developing one of the directions of descriptive approach to image analysis and recognition, and it is devoted to one of the main tools of this approach, namely, the use of formal image models in solving recognition problems. We systematized the image features widely used in solving applied problems of image analysis and recognition. It is well known that the mathematical nature and functional meaning of these features, as well as computational and measurement methods employed, are extremely various. The main results are the following: different approaches to the classification of image features are introduced, comparative analysis of them is performed, and the aspect of descriptivity is realized by numerous examples of the considered classifications being filled in by features (descriptors). On the basis of these results, certain recommendations and criteria for choosing the features in applied problems of image analysis and recognition are derived. The considered classifications of image features enable the construction of multiple-aspect image representations that preserve information essential to an applied problem. As a tool for choosing the features that depend on specific characteristics of a given problem and the initial data, we propose using parametrical generating descriptive trees, which support the creation and use of multiple-aspect image representation on the basis of different classifications of image features.