Fast Wavelet-Based Visual Classification

Simple item page
dc.creatorYu, Guoshen
dc.creatorSlotine, Jean-Jacques
dc.date2008-06-08
dc.date.accessioned2026-07-07T09:43:22Z
dc.date.available2026-07-07T09:43:22Z
dc.descriptionWe investigate a biologically motivated approach to fast visual classification, directly inspired by the recent work of Serre et al. Specifically, trading-off biological accuracy for computational efficiency, we explore using wavelet and grouplet-like transforms to parallel the tuning of visual cortex V1 and V2 cells, alternated with max operations to achieve scale and translation invariance. A feature selection procedure is applied during learning to accelerate recognition. We introduce a simple attention-like feedback mechanism, significantly improving recognition and robustness in multiple-object scenes. In experiments, the proposed algorithm achieves or exceeds state-of-the-art success rate on object recognition, texture and satellite image classification, language identification and sound classification.
dc.identifierhttps://arxiv.org/abs/0806.1446
dc.identifierhttp://arxiv.org/abs/0806.1446
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/162533
dc.subjectComputer Vision and Pattern Recognition
dc.titleFast Wavelet-Based Visual Classification
dc.typetext

Files

Collections

arXiv