Angelo Rodrigo BianchiniJosé Hiroki Saito

Semantic description of digital 3D scenes

In this work it is presented a face recognition neural network structure based in the neocognitron. The network structure is divided into two major stages: (a) Neural Network for Detection of Control Points (NNDCP), which obtains the control points to be used in the nonsupervised training structure of the neocognitron, and (b) Neural Network for the Facial Recognition (NNFR), which carried out the recognition of face samples. The main characteristic of NEOPC is the use of control points for the extraction of patterns strategically located, such as eyes, noses and lips, used on non supervised training of the NNFR. The proposed system was implemented and the results are presented.

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: