Binary partition tree as an efficient representation for image processing,segmentation, and information retrieval

This paper discusses the interest of binary partition trees as a region-ori ented image representation, Binary partition trees concentrate in a compact and structured representation a set of meaningful regions that can be extr acted from an image, They offer a multiscale representation of the image an d define a translation invariant 2-connectivity rule among regions, As show n in this paper, this representation can be used for a large number of proc essing peals such as filtering, segmentation, information retrieval and vis ual browsing. Furthermore, the processing of the tree representation leads to very efficient algorithms, Finally, for some applications, it may be int eresting to compute the binary partition tree once and to store it for subs equent use for various applications, In this context, the last section of t he paper will show that the amount of bits necessary to encode a binary par tition tree remains moderate.