A MORPHOLOGICAL DOMINANT POINTS DETECTION AND ITS CELLULAR IMPLEMENTATION

Julien Richefeu (1) , Antoine Manzanera (1)

1 RV - Robotique et Vision

This paper addresses the problem of detection of dominant points also called interest points or key points in the literature. We present a new algorithm to compute dominant points on a gray level image. It is founded on mathematical morphology, and it is adapted to SIMD cellular, level sets based, Boolean computation. It is also compliant with the morphological scale-space framework. Cellular implementation and results are presented.

Keywords: dominant point; mathematical morphology; level set; skeleton; parallel cellular machine

Domains: Computer Science [cs]; Computer Vision and Pattern Recognition [cs.CV]; Computer Science [cs]; Image Processing [eess.IV]; Computer Science [cs]; Distributed, Parallel, and Cluster Computing [cs.DC]

Julien Richefeu, Antoine Manzanera. A MORPHOLOGICAL DOMINANT POINTS DETECTION AND ITS CELLULAR IMPLEMENTATION. International Symposium on Signal Processing and its Applications (ISSPA'03), Jul 2003, Paris, France. ⟨10.1109/ISSPA.2003.1224845⟩. ⟨hal-01222697⟩