Object Recognition and Image Retrieval using the Multimodal
            Neighbourhood Colour Singature (MNS).
 
                    Jiri (George) Matas
                   matas@cmp.felk.cvut.cz
 
A novel approach to colour-based object recognition and image
retrieval the multimodal neighbourhood signature is proposed. Object
appearance is represented by colour-based features computed from image
neighbourhoods with multi-modal colour density function.  Stable
invariants are derived from modes of the density function that are
robustly located by the mean shift algorithm. The problem of
extracting local invariant colour features is addressed directly,
without a need for prior segmentation or edge detection. The signature
is concise -- an image is typically represented by a few hundred
bytes, a few thousands for very complex s cenes.

The algorithm's performance is first tested on a region-based image
retrieval task achieving a good (92\%) hit rate at a speed of 600
image comparisons per second. The method is shown to operate
successfully under changing illumination, vie wpoint and object pose,
as well as non-rigid object deformation, partial occlus ion and the
presence of background clutter dominating the scene. The performance
of the multimodal neighbourhood signature method is also evaluated on
a standar d colour object recognition task using a publicly available
dataset. Very good r ecognition performance (average match percentile
99.5\%) was achieved in real time (average 0.28 seconds for
recognising a single image) which compares favourably with results
reported in the literature.