%0 Conference Proceedings
%F Muse03a
%A Musé, P.
%A Sur, F.
%A Cao, F.
%A Gousseau, Y.
%T Unsupervised thresholds for shape matching
%B IEEE Int. Conf. on Image Processing, ICIP 2003
%C Barcelona, Spain
%X Shape recognition systems usually order a fixed number of best matches to each query, but do not address or answer the two following questions: Is a query shape in a given database ? How can we be sure that a match is correct ? This communication deals with these two key points. A database being given, with each shape S and each distance d we associate its number of false alarms NFA(S, d ), namely the expectation of the number of shapes at distance d in the database. Assume that NFA(S,d) is very small with respect to 1, and that a shape S' is found at distance d from S in the database. This match could not occur just by chance and is therefore a meaningful detection. Its explanation is usually the common origin of both shapes. Experimental evidence will show that NFA(S, d ) can be predicted accurately
%U http://www.irisa.fr/vista/Papers/2003_icip_muse.pdf
%8 September
%D 2003