Rotation-invariant HOG descriptors using Fourier analysis in polar and spherical coordinates

DOI10.1007/s11263-013-0634-zzbMath1328.68245OpenAlexW2008213480MaRDI QIDQ903448

Thorsten Schmidt, Kun Liu, Thomas Blein, Klaus Palme, Olaf Ronneberger, Henrik Skibbe, Thomas Brox

Publication date: 6 January 2016

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11263-013-0634-z

zbMATH Keywords

Fourier analysisspherical harmonicsfeature designrotation-invariancevolumetric datahistogram of oriented gradientsimage descriptor

Mathematics Subject Classification ID

Computing methodologies for image processing (68U10) Machine vision and scene understanding (68T45)

Related Items (1)

Spherical tensor algebra: a toolkit for 3D image processing

Uses Software

• LIBSVM
• LIBLINEAR
• SIFT

Cites Work

• Computing Fourier transforms and convolutions on the 2-sphere
• Support-vector networks
• Invariant kernel functions for pattern analysis and machine learning
• Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines
• A Higher-Order Structure Tensor
• Spherical Tensor Calculus for Local Adaptive Filtering
• Computing Steerable Principal Components of a Large Set of Images and Their Rotations
• Random forests
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Rotation-invariant HOG descriptors using Fourier analysis in polar and spherical coordinates