DeepAI AI Chat
Log In Sign Up

Fast Wavelet-Based Visual Classification

by   Guoshen Yu, et al.

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.


page 4

page 5


Introducing Memory and Association Mechanism into a Biologically Inspired Visual Model

A famous biologically inspired hierarchical model firstly proposed by Ri...

Parallel AdaBoost Algorithm for Gabor Wavelet Selection in Face Recognition

In this paper, the problem of automatic Gabor wavelet selection for face...

Attention Mechanisms for Object Recognition with Event-Based Cameras

Event-based cameras are neuromorphic sensors capable of efficiently enco...

End-to-End Auditory Object Recognition via Inception Nucleus

Machine learning approaches to auditory object recognition are tradition...

On The Power of Joint Wavelet-DCT Features for Multispectral Palmprint Recognition

Biometric-based identification has drawn a lot of attention in the recen...