Abstract
In this article, we present an original approach for the localization of objects in an image.Our approach is neuronal and it includes two steps. In the first step, a rough localization isperformed by presenting each pixel with its neighbourhood to a neural net which is able toindicate if this pixel and its neighbourhood are the image of the search object. This first filter isnot very discriminant for the position. From its result, we can select areas which might containan image of the...