Multichannel generalization of the Upper-Lower Edge Detector using ordered weighted averaging operators

A large number of methods in the edge detection literature are only prepared to deal with monochannel images, which represent the value at each pixel by means of scalar values. This fact hinders their applicability to many fields in which multichannel are common, including remote sensing or medical imagery. Very often, multichannel images have to be turned into grayscale images on which edge detection can be performed, but this is coupled to a loss of information that can be unbearable in certain scenarios. In this work we propose a technique for multichannel edge feature fusion technique that can be combined with any edge detection method using scalar edge features. In this way, we can extend edge detection methods by considering an initial phase of monochannel feature extraction followed by a subsequent phase of multichannel feature fusion. For the information fusion we make use of Ordered Weighted Averaging (OWA) operators, which are able to vary the relevance of each of the features to be aggregated depending upon their value. As an example, our proposal is tested with the Upper-Lower Edge Detector, despite it can be further combined with a wide range of edge detectors.