Spatial and Spectral Morphological Template Matching
Résumé
Template matching is a very topical issue in a wide range of imaging applica- tions. Mathematical morphology offers the hit-or-miss transform, an operator which has been successfully applied for template matching in binary images. More recently, it has been extended to greyscale images and even to multi- variate images. Nevertheless, these extensions, despite being relevant from a theoretical point-of-view, might lack practical interest due to the inherent diffi- culty to set up correctly the transform and its parameters (e.g. the structuring functions). In this paper, we propose a new and more intuitive operator which allows for morphological template matching in multivariate images from both a spatial and spectral point of view. We illustrate the potential of this operator in the context of remote sensing.