Title | ||
---|---|---|
A cascade of unsupervised and supervised neural networks for natural image classification |
Abstract | ||
---|---|---|
This paper presents an architecture well suited for natural image classification or visual object recognition applications. The image content is described by a distribution of local prototype features obtained by projecting local signatures on a self-organizing map. The local signatures describe singularities around interest points detected by a wavelet-based salient points detector. Finally, images are classified by using a multilayer perceptron receiving local prototypes distribution as input. This architecture obtains good results both in terms of global classification rates and computing times on different well known datasets. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11788034_10 | CIVR |
Keywords | DocType | Volume |
interest point,computing time,local signature,natural image classification,image content,local prototypes distribution,supervised neural network,local prototype,wavelet-based salient points detector,global classification rate,good result,neural network,multilayer perceptron,visual object recognition | Conference | 4071 |
ISSN | ISBN | Citations |
0302-9743 | 3-540-36018-2 | 6 |
PageRank | References | Authors |
0.44 | 14 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Julien Ros | 1 | 36 | 4.22 |
Christophe Laurent | 2 | 25 | 1.88 |
Gregoire Lefebvre | 3 | 82 | 12.13 |