This paper proposes a new texture classification system, which is distinguished by: (1) a new rotation-invariant image descriptor based on Steerable Pyramid Decomposition, and (2) by a novel multi-class recognition method based on Optimum Path Forest. By combining the discriminating power of our image descriptor and classifier, our system uses small size feature vectors to characterize texture ...

Many image-rotation invariant texture classification approaches have been presented previously. This paper proposes a novel scheme that is surface-rotation invariant. It uses the eigenvalues of a surface’s gradient-space distribution as its features. Unlike the partial derivatives, from which they are computed, these eigenvalue features are invariant to surface rotation. First we show that a si...

Classical discrete wavelet packet transforms are sensitive to changes in image orientation and translation. Therefore, it is hardly possible to extract rotation invariant features from images in the transform domain. This paper proposes several algorithms for invariant discrete wavelet decomposition to produce an invariant representation for an image. The procedure can be divided into several s...

In addition to optimal conditions, invariant laws of Lorentz, parity and time reversal are imposed to find the relation between observables (spin rotation parameters) and bilinear combination of helicity amplitudes in pion-proton elastic scattering at 6.0 GeV/c. By normalizing the differential cross-section to unity, the magnitudes of helicity amplitudes and the angle between them are dete...

In this paper, we propose Local Binary Pattern Histogram Fourier features (LBP-HF), a novel rotation invariant image descriptor computed from discrete Fourier transforms of local binary pattern (LBP) histograms. Unlike most other histogram based invariant texture descriptors which normalize rotation locally, the proposed invariants are constructed globally for the whole region to be described. ...

We consider the problem of the persistence of invariant curves for analytical fibered holomorphic transformations. We define a fibered rotation number associated to an invariant curve. We show that an invariant curve with a prescribed fibered rotation number persists under small perturbations on the dynamics provided that the pair of rotation numbers verifies a Brjuno type arithmetical condition.