Using LSTM Network in Face Classification Problems

Débora C. CorrêaDenis H. P. SalvadeoAlexandre L. M. LevadaJosé H. SaitoNelson D. A. MascarenhasJander Moreira

Many researches have used convolutional neural networks for face classification tasks. Aiming to reduce the number of training samples as well training time, we propose to use a LSTM network and compare its performance with a standard MLP network. Experiments with face images from CBCL database using PCA for feature extraction provided good results indicating that LSTM could learn properly even with reduced training set and its performance is much better than MLP.

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: