A Robust Edge-Based Corner Detector (EBCD)

Abstract

This paper presents a novel and robust edge-based corner detector (EBCD) which finds corners that are considered stable interest points in the framework of 2D object recognition especially for robot navigation. Using the EBCD, the corners are defined as intersection points of non-collinear straight image edges. The straight edge detector plus the corner detector will localize the corner positions. The detected corners have special features which are their angles and their sides length ratios. These features are invariant parameters which make the corners perfect for 2D object recognition. In addition, these corners are shown to be very robust against various image transformations like image scaling, rotation, translation and viewpoint illumination changes. Some updates are applied on the linking edge step in order to extract edges and their intersections that in turn construct the searched corners. Experiments conducted on synthetic and real images show that the proposed EBCD is able to achieve a very good performance in terms of accuracy, stability and especially computational efficiency in comparison with existing algorithms on interest points.