Fast recursive ensemble convolution of haar-like features

Daniel Wesierski; Maher Mkhinini; Patrick Horain; Anna Jezierska

doi:10.1109/CVPR.2012.6248115

Fast recursive ensemble convolution of haar-like features

Daniel Wesierski ¹ Maher Mkhinini ¹ Patrick Horain ¹ Anna Jezierska ²

1 EPH - Département Electronique et Physique

2 LIGM - Laboratoire d'Informatique Gaspard-Monge

Abstract : Haar-like features are ubiquitous in computer vision, e.g. for Viola and Jones face detection or local descriptors such as Speeded-Up-Robust-Features. They are classically computed in one pass over integral image by reading the values at the feature corners. Here we present a new, general, parsing formalism for convolving them more efficiently. Our method is fully automatic and applicable to an arbitrary set of Haar-like features. The parser reduces the number of memory accesses which are the main computational bottleneck during convolution on modern computer architectures. It first splits the features into simpler kernels. Then it aligns and reuses them where applicable forming an ensemble of recursive convolution trees, which can be computed faster. This is illustrated with experiments, which show a significant speed-up over the classic approach.

Keywords : Computer architecture Convolution Face detection Feature extraction Kernel Vectors

Type de document :

Communication dans un congrès

CVPR "12 : IEEE Conference on Computer Vision and Pattern Recognition, Jun 2012, Providence, Rhode Island, United States. IEEE, pp.3689-3696, 2012, 〈10.1109/CVPR.2012.6248115〉

Domaine :

Informatique [cs] / Vision par ordinateur et reconnaissance de formes [cs.CV]

Liste complète des métadonnées

Littérature citée [17 références] Voir Masquer Télécharger

https://hal.archives-ouvertes.fr/hal-00819740
Contributeur : Médiathèque Télécom Sudparis & Télécom Ecole de Management <>
Soumis le : jeudi 2 mai 2013 - 10:55:37
Dernière modification le : mercredi 11 avril 2018 - 12:12:02
Document(s) archivé(s) le : lundi 19 août 2013 - 11:05:45

Wesierski_2012_cvpr.pdf

Fichiers produits par l'(les) auteur(s)

Fast recursive ensemble convolution of haar-like features

Fichier

Identifiants

Collections

Citation

Exporter

Métriques

220

95

Contact

Fast recursive ensemble convolution of haar-like features

Fichier

Identifiants

Collections

Citation

Exporter

Partager

Métriques

220

95

Contact