Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination

An affine invariant representation is constructed with a cascade of invariants, which preserves information for classification. A joint translation and rotation invariant representation of image patches is calculated with a scattering transform. It is implemented with a deep convolution network, which computes successive wavelet transforms and modulus non-linearities. Invariants to scaling, shearing and small deformations are calculated with linear operators in the scattering domain. State-of-the-art classification results are obtained over texture databases with uncontrolled viewing conditions.

[1]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[2]  Cordelia Schmid,et al.  A sparse texture representation using local affine regions , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Giovanna Citti,et al.  A Cortical Based Model of Perceptual Completion in the Roto-Translation Space , 2006, Journal of Mathematical Imaging and Vision.

[4]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[5]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[6]  Bernhard Burgeth,et al.  Scale Spaces on Lie Groups , 2007, SSVM.

[7]  Thomas Serre,et al.  Robust Object Recognition with Cortex-Like Mechanisms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Lewis D. Griffin,et al.  Texture classification with a dictionary of basic image features , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Yann LeCun,et al.  Convolutional networks and applications in vision , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[10]  Yong Xu,et al.  A new texture descriptor using multifractal analysis in multi-orientation wavelet pyramid , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Stéphane Mallat,et al.  Group Invariant Scattering , 2011, ArXiv.

[12]  Hongbin Zha,et al.  Sorted Random Projections for robust texture classification , 2011, 2011 International Conference on Computer Vision.

[13]  Huu-Giao Nguyen,et al.  Visual textures as realizations of multivariate log-Gaussian Cox processes , 2011, CVPR 2011.

[14]  Jean-Paul Gauthier,et al.  Anthropomorphic Image Reconstruction via Hypoelliptic Diffusion , 2010, SIAM J. Control. Optim..

[15]  Lorenzo Rosasco,et al.  The computational magic of the ventral stream: sketch of a theory (and why some deep architectures work). , 2012 .

[16]  Stéphane Mallat,et al.  Invariant Scattering Convolution Networks , 2012, IEEE transactions on pattern analysis and machine intelligence.