V1-Inspired features induce a weighted margin in SVMs

Authors:
Hilton Bristow;Simon Lucey
Affiliations:
Queensland University of Technology, Australia,Commonwealth Scientific and Industrial Research Organisation, Australia;Commonwealth Scientific and Industrial Research Organisation, Australia
Venue:
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Year:
2012

Citing 8
Cited 0

Distortion Invariant Object Recognition in the Dynamic Link Architecture

IEEE Transactions on Computers
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
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
LIBLINEAR: A Library for Large Linear Classification

The Journal of Machine Learning Research
Reinterpreting the Application of Gabor Filters as a Manipulation of the Margin in Linear Support Vector Machines

IEEE Transactions on Pattern Analysis and Machine Intelligence
Gabor feature based sparse representation for face recognition with gabor occlusion dictionary

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Registration Invariant Representations for Expression Detection

DICTA '10 Proceedings of the 2010 International Conference on Digital Image Computing: Techniques and Applications
Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Image representations derived from simplified models of the primary visual cortex (V1), such as HOG and SIFT, elicit good performance in a myriad of visual classification tasks including object recognition/detection, pedestrian detection and facial expression classification. A central question in the vision, learning and neuroscience communities regards why these architectures perform so well. In this paper, we offer a unique perspective to this question by subsuming the role of V1-inspired features directly within a linear support vector machine (SVM). We demonstrate that a specific class of such features in conjunction with a linear SVM can be reinterpreted as inducing a weighted margin on the Kronecker basis expansion of an image. This new viewpoint on the role of V1-inspired features allows us to answer fundamental questions on the uniqueness and redundancies of these features, and offer substantial improvements in terms of computational and storage efficiency.