Advanced scale-space, invariant, low detailed feature recognition from images - car brand recognition

Abstract

This paper presents analysis of a model for car brand recognition. The used method is an invariant keypoint detector - descriptor. An input for the method is a set of images obtained from the real environment. The task of car classification according its brand is not a trivial task. Our work would be a part of an intelligent traffic system where we try to collect some statistics about various cars passing a given area. It is difficult to recognize objects when they are in different scales, rotated or if they are low contrasted or when it is necessary to take into count high level of details. In our work we present a system for car brand recognition. We use scale space invariant keypoint detector and descriptor (SURF - Speeded-up Robust Features) for this purpose.