Home Sponsors History Contact
     Call for Participation
     Program
     Organizers
     Workshops & Tutorials
     Paper Submissions
     Call for Demo & Exhibitions
     Registration
     Key Dates
     Venue














Tutorial: Face Analysis Using Local Binary Pattern Variants

Abdenour Hadid
University of Oulu

Date: Monday, March 21
Time: 1:30pm to 5:00pm
Location: Anacapa/Santa Cruz/Santa Rosa

Recent developments showed that the local binary pattern (LBP) texture method provides outstanding results in representing and analyzing faces in both still images and video sequences. The LBP operator is defined as a gray-scale invariant texture measure, derived from a general definition of texture in a local neighbourhood. Due to its discriminative power and computational simplicity, the LBP texture operator has become a highly popular approach in various computer vision applications, including visual inspection, image retrieval, remote sensing, biomedical image analysis, face image analysis, motion analysis, environment modelling, and outdoor scene analysis.

LBP has been highly successful in numerous applications around the world and has inspired plenty of new research on related methods. Since the introduction of the basic LBP operator, several variants have been proposed to improve the discriminative power and robustness of the operator.

This tutorial focuses on the application of the LBP approach and its recent variants to face analysis. First the theoretical foundations of the basic LBP operators in spatial and spatiotemporal domains are presented. Then, some recent LBP variants which improve the discriminative power and robustness of the original LBP are described. An overview and results of applying LBP to various face analysis related tasks, including face recognition, face detection, facial expression recognition, visual-speech recognition, and gender classification, are then given. Finally, directions for future research are discussed.

After the course, the participants will understand the fundamental theory behind the local binary pattern approach and will be advised on effective and proper use in various face-related problems. With the provided source code and material, the participants will be ready to use LBP in their own research.

    Outline:
  1. Introduction
  2. Local Binary Pattern texture operator (LBP)
    a. LBP in spatial domain
    b. LBP in spatiotemporal domain
  3. LBP variants
  4. Methods and applications in face analysis
    a. Face detection and recognition from still images
    b. Face and facial expression recognition from videos
    c. Gender classification
    d. Visual speech recognition
    e. LBP in other face-related problems
  5. Source codes, resources, conclusions and future directions




Latest News at FG

   

FG 2011 was a success, with great keynote talks, an excellent program of presentations, posters, demos, and exhibits, as well as five workshops and three tutorials. Thanks to everyone whose efforts made the conference possible!

The proceedings will be available at IEEE Xplore in the near future. The location and organizers of FG 2013 will be announced here soon.


Registration hours

*Weather Update* - The weather forecast for the week of FG is not good - rainy and relatively cool. Bring an umbrella if you can!

Santa Barbara weather - 5-day forecast

No health risk to California from radiation

UCSB Allosphere tour

All conference presenters: please see the Information for Presenters.

The final program is available for the main conference.

Tutorials will be presented at FG 2011 on Monday and Friday. See the list and schedule of tutorials and workshops.

Scheduled keynote speakers