eprintid: 670
rev_number: 13
eprint_status: archive
userid: 14
dir: disk0/00/00/06/70
datestamp: 2014-12-05 14:00:41
lastmod: 2015-05-29 20:18:00
status_changed: 2014-12-05 14:00:41
type: report
metadata_visibility: show
item_issues_count: 0
creators_name: Coskun, E.
creators_name: Elson, T.
creators_name: Lim, S.
creators_name: Matthews, J.
creators_name: Morris, G.
creators_name: Nowaczyk, N.
creators_name: Raanes, P. N.
creators_name: Wind, D. K.
corp_creators: Matt Celuszak
corp_creators: Daniel Jabry
title: Gabor Filter Selection and Computational Processing for Emotion Recognition
ispublished: pub
subjects: tech_dev
subjects: data
studygroups: ESGI100
companyname: CrowdEmotion
full_text_status: public
abstract: CrowdEmotion produce software to measure a person’s emotions based on analysis of microfacial expressions detected using a webcam. The technology relies on a machine learning algorithm to recognize which features correspond with which emotions; it is trained on a labelled dataset. The features are derived by applying a bank of Gabor filters to a set of frames, determining the Local Binary Pattern (LBP) of each resulting pixel, and then averaging the results over three orthogonal planes (TOP), as outlined in [1]. CrowdEmotion challenged the study group to improve the accuracy, processing speed and cost-efficiency of the tool. In particular they wanted to know if a subset of the bank of Gabor filters was sufficient, and whether the image filtering stage could be implemented on a GPU. A framework for choosing the optimum set of Gabor filters was established, and preliminary testing performed. Different ways of implementing Gabor filters were explored. Some ele- ments of the feature set give little information, thus ways of reducing the dimensionality of this were interrogated. Some steps in the procedure outlined in [1] seemed ad-hoc, in particular when taking a subset of LBPs and choosing a gridding pattern to perform the TOP step. Taking a subset of LBPs was found to be fully justified. Meanwhile choosing a gridding pattern is open to interpretation; we make some suggestions on how this choice might be improved. A short review of alternatives to using a SVM as a classifier is presented.
date: 2014
citation:   Coskun, E. and Elson, T. and Lim, S. and Matthews, J. and Morris, G. and Nowaczyk, N. and Raanes, P. N. and Wind, D. K.  (2014) Gabor Filter Selection and Computational Processing for Emotion Recognition.  [Study Group Report]     
document_url: http://miis.maths.ox.ac.uk/miis/670/1/esgi100-gabor-filter.pdf