Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

Loglet SIFT for part description in deformable part models : application to face alignment

Tools
- Tools
+ Tools

Zhang, Qiang and Bhalerao, Abhir (2016) Loglet SIFT for part description in deformable part models : application to face alignment. In: British Machine Vision Conference (BMVC 2016), York, UK, 19-22 Sep 2016. Published in: Proceedings of the British Machine Vision Conference (BMVC) 31.1-31.12. ISBN 1901725596. doi:10.5244/C.30.31

[img] PDF
WRAP_zhang-bhalerao-bmvc-2016_.pdf - Accepted Version - Requires a PDF viewer.

Download (8Mb)
Official URL: https://dx.doi.org/10.5244/C.30.31

Request Changes to record.

Abstract

We focus on a novel loglet-SIFT descriptor for the parts representation in the De- formable Part Models (DPM). We manipulate the feature scales in the Fourier domain and decompose the image into multi-scale oriented gradient components for computing SIFT. The scale selection is controlled explicitly by tiling Log-wavelet functions (loglets) on the spectrum. Then oriented gradients are obtained by adding imaginary odd parts to the loglets, converting them into differential filters. Coherent feature scales and domain sizes are further generated by spectrum cropping. Our loglet gradient filters are shown to compare favourably against spatial differential operators, and have a straightforward and efficient implementation. We present experiments to validate the performance of the loglet-SIFT descriptor which show it to improve the DPM using a supervised descent method by a significant margin.

Item Type: Conference Item (Paper)
Subjects: Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
Divisions: Faculty of Science, Engineering and Medicine > Science > Computer Science
Library of Congress Subject Headings (LCSH): Image processing -- Digital techniques
Journal or Publication Title: Proceedings of the British Machine Vision Conference (BMVC)
Publisher: BMVA Press
ISBN: 1901725596
Official Date: 19 September 2016
Dates:
DateEvent
19 September 2016Published
15 July 2016Accepted
Page Range: 31.1-31.12
Article Number: 31
DOI: 10.5244/C.30.31
Status: Peer Reviewed
Publication Status: Published
Access rights to Published version: Open Access
Description:

Editors: Richard C. Wilson, Edwin R. Hancock and William A. P. Smith

Conference Paper Type: Paper
Title of Event: British Machine Vision Conference (BMVC 2016)
Type of Event: Conference
Location of Event: York, UK
Date(s) of Event: 19-22 Sep 2016
Open Access Version:
  • Other

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics

twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us