Finding Corners

Many important image cues such as 'T'-,'X'and 'L'junctions have a local two-dimensional structure. Conventional edge detectors are designed for one-dimensional 'events'. Even the best edge operators can not reliably detect these two-dimensional features. This contribution proposes a solution to the two-dimensional problem. In this paper, I address the following: • 'L'-junction detection. Previous attempts, relying on the second differentials of the image surface have essentially measured image curvature. Recently Harris [Harris 87] implemented a 'corner' detector that is based only on first differentials. I provide a mathematical proof to explain how this algorithm estimates image curvature. Although this algorithm will isolate image 'L'junctions, its performance cannot be predicted for T'-junctions and other higher order image structures. • Instead, an image representation is proposed that exploits the richness of the local differential geometrical 'topography ' of the intensity surface. Theoretical and experimental results are presented which demonstrate how idealised instances of two-dimensional surface features such as junctions can be characterised by the differential geometry of a simple facet model. • Preliminary results are very encouraging. Current studies are concerned with the extension to real data. I am investigating statistical noise models to provide a measure of 'confidence' in the geometric labelling. The richness and sparseness of a two-dimensional structure can be exploited in many high-level vision processes. I intend to use my representation to explore some of these fields in future work.