Abstract
A wavelet scattering network computes a translation invariant image representation which is stable to deformations and preserves high-frequency information for classification. It cascades wavelet transform convolutions with nonlinear modulus and averaging operators. The first network layer outputs SIFT-type descriptors, whereas the next layers provide complementary invariant information that improves classification. The mathematical analysis of wavelet scattering networks explains important properties of deep convolution networks for classification. A scattering representation of stationary processes incorporates higher order moments and can thus discriminate textures having the same Fourier power spectrum. State-of-the-art classification results are obtained for handwritten digits and texture discrimination, with a Gaussian kernel SVM and a generative PCA classifier.
Keywords
Pattern recognition (psychology)Artificial intelligenceWaveletInvariant (physics)Wavelet transformConvolution (computer science)MathematicsContextual image classificationFourier transformFeature extractionKernel (algebra)Computer scienceArtificial neural networkMathematical analysisImage (mathematics)Pure mathematics
Affiliated Institutions
Related Publications
PCA-SIFT: a more distinctive representation for local image descriptors
Stable local feature detection and representation is a fundamental component of many image registration and object recognition algorithms. Mikolajczyk and Schmid (June 2003) rec...
Radon transform orientation estimation for rotation invariant texture analysis
This paper presents a new approach to rotation invariant texture classification. The proposed approach benefits from the fact that most of the texture patterns either have direc...
Scale-invariant heat kernel signatures for non-rigid shape recognition
One of the biggest challenges in non-rigid shape retrieval and comparison is the design of a shape descriptor that would maintain invariance under a wide class of transformation...
A theory for multiresolution signal decomposition: the wavelet representation
Multiresolution representations are effective for analyzing the information content of images. The properties of the operator which approximates a signal at a given resolution w...
BOOSTING PERFORMANCE IN NEURAL NETWORKS
A boosting algorithm, based on the probably approximately correct (PAC) learning model is used to construct an ensemble of neural networks that significantly improves performanc...
Publication Info
- Year
- 2013
- Type
- article
- Volume
- 35
- Issue
- 8
- Pages
- 1872-1886
- Citations
- 1576
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
1576
OpenAlex
Cite This
Joan Bruna,
Stéphane Mallat
(2013).
Invariant Scattering Convolution Networks.
IEEE Transactions on Pattern Analysis and Machine Intelligence
, 35
(8)
, 1872-1886.
https://doi.org/10.1109/tpami.2012.230
Identifiers
- DOI
- 10.1109/tpami.2012.230