Automatic hardware implementation tool for a discrete Adaboost-based decision algorithm

Catégorie

Journal Article

Auteurs

Mitéran, J., Matas, J., Bourennane, E., Paindavoine, M., Dubois, J.

Année

2005

Titre

Automatic hardware implementation tool for a discrete Adaboost-based decision algorithm

Journal / Livre / Conférence

EURASIP Journal on Applied Signal Processing

Résumé

We propose a method and a tool for automatic generation of hardware implementation of a decision rule based on the Adaboost algorithm. We review the principles of the classification method and we evaluate its hardware implementation cost in terms of FPGA's slice, using different weak classifiers based on the general concept of hyperrectangle. The main novelty of our approach is that the tool allows the user to find automatically an appropriate tradeoff between classification performances and hardware implementation cost, and that the generated architecture is optimized for each training process. We present results obtained using Gaussian distributions and examples from UCI databases. Finally, we present an example of industrial application of real-time textured image segmentation.

Issue

7

Volume

2005

Pages

1035-1046

Téléchargement

Télécharger cette publication au format PDF

‹ Retour à la page précédente