OBJECTS RECOGNITION BY MEANS OF PROJECTIVE INVARIANTS CONSIDERING CORNER-POINTS.

This paper presents an object recognition technique based on projective geometry for industrial pieces that satisfy geometric properties. First at all, we consider some methods of corner detection which are useful for the extraction of interest points in digital images. For object recognition by means of projective invariants, an excessive number of points to be processed supposes a greater complexity of the algorithm We present a method that allows to reduce the points extracted by different corner detection techniques, based on the elimination of non-significant points, using the estimation of the straight lines that contain those points. Secondly, these groups of points are then used to build projective invariants which allow us to distinguish one object from another. Experiments with different pieces and real images in grey-scale show the validity of this approach