Multi scale Harris corner detector based on Differential Morphological Decomposition

In this paper, a novel method for multi scale corner analysis and detection is presented. First, state-of-the-art Harris–Laplace corner detector is reminded, which benefits from linear scale-space analysis. Secondly, a non-linear scale-space transform, namely Differential Morphological Decomposition, is described. This multi-scale transform is used jointly with the Harris corner indicator to build a new multi scale corner detector. Both corner detectors are visually assessed on synthetic and satellite images, highlighting the advantages of such a method.

► The proposed multi-scale corner detector is localized in scale and space.
► It discriminates the corner scales better than Harris–Laplace corner detector.
► It is suited to extract salient points in satellite images.