SHOG: spherical HOG descriptors for rotation invariant 3D object detection

Authors:
Henrik Skibbe;Marco Reisert;Hans Burkhardt
Affiliations:
Department of Computer Science, University of Freiburg, Germany and Center for Biological Signalling Studies, University of Freiburg;Dept. of Diagnostic Radiology, Medical Physics, University Medical Center, Freiburg;Department of Computer Science, University of Freiburg, Germany and Center for Biological Signalling Studies, University of Freiburg
Venue:
DAGM'11 Proceedings of the 33rd international conference on Pattern recognition
Year:
2011

Citing 4
Cited 1

Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Harmonic Filters for Generic Feature Detection in 3D

Proceedings of the 31st DAGM Symposium on Pattern Recognition
3D invariants with high robustness to local deformations for automated pollen recognition

Proceedings of the 29th DAGM conference on Pattern recognition

Rotation-Invariant HOG Descriptors Using Fourier Analysis in Polar and Spherical Coordinates

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a method for densely computing local spherical histograms of oriented gradients (SHOG) in volumetric images. The descriptors are based on the continuous representation of the orientation histograms in the harmonic domain, which we compute very efficiently via spherical tensor products and the Fast Fourier Transformation. Building upon these local spherical histogram representations, we utilize the Harmonic Filter to create a generic rotation invariant object detection system that benefits from both the highly discriminative representation of local image patches in terms of histograms of oriented gradients and an adaptable trainable voting scheme that forms the filter. We exemplarily demonstrate the effectiveness of such dense spherical 3D descriptors in a detection task on biological 3D images. In a direct comparison to existing approaches, our new filter reveals superior performance.