V1-inspired features induce a weighted margin in SVMs

Bristow, Hilton & Lucey, Simon (2012) V1-inspired features induce a weighted margin in SVMs. In Lecture Notes in Computer Science : Proceedings of the 12th European Conference on Computer Vision : Part II, Springer, Florence, Italy, pp. 59-72.

View at publisher

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.

Impact and interest:

0 citations in Scopus
Search Google Scholar™

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

108 since deposited on 06 Mar 2013
11 in the past twelve months

Full-text downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 57843
Item Type: Conference Paper
Refereed: Yes
Additional URLs:
Keywords: V1, SVM, Histograms of Oriented Gradients, Support Vector Machine, Features
DOI: 10.1007/978-3-642-33709-3_5
ISBN: 9783642337093
ISSN: 1611-3349
Subjects: Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING (080100) > Computer Vision (080104)
Divisions: Past > QUT Faculties & Divisions > Faculty of Built Environment and Engineering
Past > Institutes > Information Security Institute
Copyright Owner: Copyright 2012 Springer
Copyright Statement: The original publication is available at SpringerLink
http://www.springerlink.com
Deposited On: 06 Mar 2013 22:41
Last Modified: 14 May 2015 22:17

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page