Abstract | ||
---|---|---|
A scattering transform defines a signal representation which is invariant to translations and Lipschitz continuous relatively to deformations. It is implemented with a non-linear convolution network that iterates over wavelet and modulus operators. Lipschitz continuity locally linearizes deformations. Complex classes of signals and textures can be modeled with low-dimensional affine spaces, computed with a PCA in the scattering domain. Classification is performed with a penalized model selection. State of the art results are obtained for handwritten digit recognition over small training sets, and for texture classification. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/IVMSPW.2011.5970362 | Ithaca, NY |
Keywords | Field | DocType |
image classification,transforms,Lipschitz continuity,PCA,handwritten digit recognition,image classification,invariant scattering transform representation,modulus operator,nonlinear convolution network,signal representation,Image classification,Invariant representations,local image descriptors,pattern recognition,texture classification | Affine transformation,Pattern recognition,Convolution,Algorithm,Artificial intelligence,Lipschitz continuity,Invariant (mathematics),Operator (computer programming),Contextual image classification,Mathematics,Wavelet,Wavelet transform | Journal |
Volume | ISBN | Citations |
abs/1112.1120 | 978-1-4577-1284-5 | 1 |
PageRank | References | Authors |
0.35 | 12 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
J. Bruna | 1 | 1697 | 82.95 |
Stéphane Mallat | 2 | 4107 | 718.30 |