Object recognition with the HOSVD of the multi-model space-variant pattern tensors

Authors:
Bogusław Cyganek
Affiliations:
AGH University of Science and Technology, Kraków, Poland
Venue:
CAIP'11 Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part I
Year:
2011

Citing 8
Cited 0

A Multilinear Singular Value Decomposition

SIAM Journal on Matrix Analysis and Applications
Multilinear Analysis of Image Ensembles: TensorFaces

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
A novel method for detecting lips, eyes and faces in real time

Real-Time Imaging - Special issue on spectral imaging
An Introduction to 3D Computer Vision Techniques and Algorithms

An Introduction to 3D Computer Vision Techniques and Algorithms
Handwritten digit classification using higher order singular value decomposition

Pattern Recognition
A visual approach for driver inattention detection

Pattern Recognition
Circular road signs recognition with soft classifiers

Integrated Computer-Aided Engineering - Artificial Neural Networks
Robust real-time eye detection and tracking under variable lighting conditions and various face orientations

Computer Vision and Image Understanding - Special issue on eye detection and tracking

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper presents a framework for object recognition with the multimodel space-variant approach in the log-polar domain built into the multilinear tensor classifier. Thanks to this the method allows recognition of rotated and/or scaled objects taking advantage of the foveal and peripheral information. Recognition is done in the multilinear subspaces obtained after the higher-order singular value decomposition of the pattern tensor. The experiments show high accuracy and robustness of the proposed method.