Combined scattering for rotation invariant texture analysis.

The European Symposium on Artificial Neural NetworksPublished 1 January 2012

Laurent Sifre, Stéphane Mallat

Citations58

TL;DR

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.

Abstract

This paper introduces a combined scattering representation for texture classification, which is invariant to rotations and stable to deformations. A combined scattering is computed with two nested cascades of wavelet transforms and complex modulus, along spatial and rotation variables. Results are compared with state-of-the-art algorithms, with a nearest neighbor classifier.

Keywords

Computer Science

IEEE Transactions on Pattern Analysis and Machine IntelligenceMultiresolution gray-scale and rotation invariant texture classification with local binary patterns

15,254 Citations2002Timo Ojala, Matti Pietikäinen +1 more

A generalized gray-scale and rotation invariant operator presentation that allows for detecting the "uniform" patterns for any quantization of the angular space and for any spatial resolution and presents a method for combining multiple operators for multiresolution analysis.

Convolutional networks and applications in vision

2,138 Citations2010Yann LeCun, Koray Kavukcuoglu +1 more

New unsupervised learning algorithms, and new non-linear stages that allow ConvNets to be trained with very few labeled samples are described, including one for visual object recognition and vision navigation for off-road mobile robots.

View PDF

IEEE Transactions on Image ProcessingTexture classification and segmentation using wavelet frames

1,311 Citations1995Michaël Unser

Outex - new framework for empirical evaluation of texture analysis algorithms

690 Citations2003Timo Ojala, Topi Mäenpää +4 more

The proposed Outex framework contains a large collection of surface textures captured under different conditions, which facilitates construction of a wide range of texture analysis problems.

Pattern RecognitionBrief review of invariant texture analysis methods

447 Citations2002Jianguo Zhang, Tieniu Tan

This paper considers invariant texture analysis, and approaches whose performances are not affected by translation, rotation, affine, and perspective transform are addressed.

Lecture notes in computer scienceRotation Invariant Image Description with Local Binary Pattern Histogram Fourier Features

405 Citations2009Timo Ahonen, Jiřı́ Matas +2 more

In the experiments, it is shown that these features outperform non-invariant and earlier version of rotation invariant LBP and the MR8 descriptor in texture classification, material categorization and face recognition tests.

IEE Proceedings - Vision Image and Signal ProcessingRobust rotation-invariant texture classification: wavelet, Gabor filter and GMRF based schemes

188 Citations1997Robert P. Porter, Nishan Canagarajah

Three novel feature extraction schemes for texture classification are proposed, indicating that the wavelet-based approach is the most accurate, exhibits the best noise performance and has the lowest computational complexity.

A fully affine invariant image comparison method

136 Citations2009Guoshen Yu, Jean‐Michel Morel

Affine-SIFT (ASIFT) is introduced, a fully affine invariant image comparison method that permits to reliably identify features that have undergone very large affine distortions measured by a new parameter, the transition tilt.

Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern RecognitionRotation invariant local phase quantization for blur insensitive texture analysis

135 Citations2008Ville Ojansivu, Esa Rahtu +1 more

A rotation invariant extension to the blur insensitive local phase quantization texture descriptor that applies the phase of the locally computed Fourier transform coefficients to be insensitive to centrally symmetric image blurring.

Classification with scattering operators

129 Citations2011Joan Bruna, Stéphane Mallat

A scattering vector is a local descriptor including multiscale and multi-direction co-occurrence information and is computed with a cascade of wavelet decompositions and complex modulus.