HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Fast recursive ensemble convolution of haar-like features

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.
Document type :
Conference papers
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download

Contributor : Médiathèque Télécom Sudparis & Institut Mines-Télécom Business School Connect in order to contact the contributor
Submitted on : Thursday, May 2, 2013 - 10:55:37 AM
Last modification on : Saturday, January 15, 2022 - 3:56:42 AM
Long-term archiving on: : Monday, August 19, 2013 - 11:05:45 AM


Files produced by the author(s)



Daniel Wesierski, Maher Mkhinini, Patrick Horain, Anna Jezierska. Fast recursive ensemble convolution of haar-like features. CVPR "12 : IEEE Conference on Computer Vision and Pattern Recognition, Jun 2012, Providence, Rhode Island, United States. pp.3689-3696, ⟨10.1109/CVPR.2012.6248115⟩. ⟨hal-00819740⟩



Record views


Files downloads