Computer Science – Computer Vision and Pattern Recognition
Scientific paper
2008-06-08
Computer Science
Computer Vision and Pattern Recognition
Scientific paper
We 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.
Slotine Jean-Jacques
Yu Guoshen
No associations
LandOfFree
Fast Wavelet-Based Visual Classification does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Fast Wavelet-Based Visual Classification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fast Wavelet-Based Visual Classification will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-65816