Classification with scattering operators

@article{Bruna2011ClassificationWS,
  title={Classification with scattering operators},
  author={Joan Bruna and St{\'e}phane Mallat},
  journal={CVPR 2011},
  year={2011},
  pages={1561-1566}
}
A scattering vector is a local descriptor including multiscale and multi-direction co-occurrence information. It is computed with a cascade of wavelet decompositions and complex modulus. This scattering representation is locally translation invariant and linearizes deformations. A supervised classification algorithm is computed with a PCA model selection on scattering vectors. State of the art results are obtained for handwritten digit recognition and texture classification. 

Figures and Tables from this paper

Combined scattering for rotation invariant texture analysis

A combined scattering representation for texture classification is introduced, which is invariant to rotations and stable to deformations, and compared with state-of-the-art algorithms, with a nearest neighbor classifier.

Applying scattering operators for face recognition: A comparative study

A local descriptor, scattering operator, which includes multi-scale and multi-direction co-occurrence information, which is computed with a cascade of wavelet decompositions and complex modulus and can linearize deformations.

Monogenic Wavelet Scattering Network for Texture Image Classification

This work proposes a novel Monogenic Wavelet Scattering Network (MWSN) for 2D texture image classification through a cascade of monogenic wavelet filtering with nonlinear modulus and averaging operators by replacing the 2D Morlet wavelets in the standard STN.

Deep learning for texture classification via multi-wavelet fusion of scattering transforms

A multi-wavelet fusion-based architecture to improve the error of classification by using scattering transforms that achieves better classification results compared to the original scattering transform, and thus can be used as an effective method for texture classification problems.

Palmprint recognition using deep scattering network

The proposed scheme has been tested on a well-known palmprint database and achieved accuracy rates of 99.4% and 99.9% using minimum distance classifier and SVM respectively, outperforming previous algorithms on this dataset.

Convolution Networks with Stable Invariants

A particular class of convolution networks are constructed, that implement non-linear scattering operators, that linearize small deformations and are proved to build invariant representations to translations and to any prescribed compact group.

Fingerprint recognition using translation invariant scattering network

  • Shervin MinaeeYao Wang
  • Computer Science
    2015 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)
  • 2015
The proposed algorithm is one of the first works which explores the application of deep architecture for fingerprint recognition and has shown promising results with the best accuracy rate of 98%.

Palmprint Recognition Using Deep Scattering Convolutional Network

A powerful image representation, called scattering network/transform, is used for palmprint recognition, and their dimensionality is reduced by applying principal component analysis (PCA) which reduces the computational complexity of the recognition task.

Image recognition performed on handwritten letters using the windowed scattering transform

The construction of the windowed scattering transform and its numerical approximation is explained in detail and examples showcasing the properties of the transform are presented, and the transform applied in image recognition on a dataset of handwritten letters.

Image Classification with Hybrid Shearlet Scattering Networks

  • Qingyun RenBingyin ZhouW. Guo
  • Mathematics, Computer Science
    2019 11th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)
  • 2019
A shearlett scattering transform which uses the cascade of shearlet transforms and modulus non-linearities to obtain invariant image representations to improve the sparsity of the previous scattering transform using Morlet.
...

References

SHOWING 1-10 OF 24 REFERENCES

Recursive interferometric representations

Recursive interferometry computes invariants with a cascade of complex wavelet transforms and modulus operators and provides invariant representations of stationary processes that preserve signal classes.

A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients

A universal statistical model for texture images in the context of an overcomplete complex wavelet transform is presented, demonstrating the necessity of subgroups of the parameter set by showing examples of texture synthesis that fail when those parameters are removed from the set.

Tangent distance kernels for support vector machines

This work introduces a new class of kernels for support vector machines which incorporate tangent distance and therefore are applicable in cases where such transformation invariances are known.

Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition

An unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions that alleviates the over-parameterization problems that plague purely supervised learning procedures, and yields good performance with very few labeled training samples.

Distinctive Image Features from Scale-Invariant Keypoints

This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are ...

A Statistical Approach to Material Classification Using Image Patch Exemplars

It is demonstrated that materials can be classified using the joint distribution of intensity values over extremely compact neighborhoods (starting from as small as 3times3 pixels square) and that this can outperform classification using filter banks with large support.

Task-Driven Dictionary Learning

This paper presents a general formulation for supervised dictionary learning adapted to a wide variety of tasks, and presents an efficient algorithm for solving the corresponding optimization problem.

Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons

A unified model to construct a vocabulary of prototype tiny surface patches with associated local geometric and photometric properties, represented as a set of linear Gaussian derivative filter outputs, under different lighting and viewing conditions is provided.

Rotation invariant texture classification using LBP variance (LBPV) with global matching