The Community for Technology Leaders
Green Image
<p><b>Abstract</b>—Based on deformable templates, the paper formulates an integrated and flexible Bayesian recognition system of multiple occluded objects. Various local dependence properties of the model are obtained to reduce the computational cost with the increase in the number of objects. Numerical results for a synthetic image and for a real image of mushrooms are discussed.</p>
Bayesian methods, deformable templates, iterative conditional increase, iterative conditional mode, Markov random field, object ordering, object process, occlusion, response function.

K. M. de Souza, W. Qian, K. V. Mardia and D. Shah, "Deformable Template Recognition of Multiple Occluded Objects," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 19, no. , pp. 1035-1042, 1997.
88 ms
(Ver 3.3 (11022016))