Conference Paper (international conference)
serial: Proceedings of the 15th International Conference on Pattern Recognition, p. 585-589 , Eds: Sanfeliu A., Villanueva J. J., Vanrell M.
publisher: IEEE Computer Society, (Los Alamitos 2000)
action: International Conference on Pattern Recognition /15./, (Barcelona, ES, 03.09.2000-07.09.2000)
project(s): IAA2075703, GA AV, VS96063, MŠMT, ME 187, MŠMT
As shown recently, the structural optimization of probabilistic neural networks can be included into EM algorithm by introducing a special type of mixtures. The method has been applied to recognize unconstrained handwritten numerals from the database of Concordia University in Montreal. In the present paper we discuss the possibility of a proper initialization of EM algorithm for estimating the class-conditional multivariate Bernoulli mixtures.