Inductive generation of icon trees in foveated multi-resolution recognition
Sylvain Brugnot · 1999
INTRODUCTION Iconic approaches Fisher (2) to object recognition rely upon the direct comparison between an unknown input image with of characteristic views of images of a target subject contained in an icon database. Hence, this approach to recognition is distinguished by making comparisons in icon-space as opposed to making comparisons upon a more condensed symbolic representation of the information contained within the database and unknown images. The appeal of the iconic approach is in its algorithmic simplicity, which is traded for increased memory utilisation. However, to be tractable some method of interpolating between the sampled views of the subject is usually necessary. It is also possible to constrain the visual search-space by adopting transformations that confer some form of viewpoint invariance. The RC (retino-cortical) transform, Wilson (3), a close cousin to the complex log transform, has long been used in this capacity and confers both rotational and