Efficacy of Biophysiological Measurements at FTFPs for Facial Expression Classification: A Validation

Recent works suggest that thermal intensity values (TIVs) measured around the facial thermal feature points (FTFPs) can help in distinguishing between the facial expression of affective states. This work investigates if the average pixel grey-levels, instead of TIVs, measured in sub-image masks arou...

Full description

Bibliographic Details
Main Authors: Khan, Masood Mehmood, Oz, Ihsan
Other Authors: Yuan-Ting Zhang
Format: Conference Paper
Published: IEEE Engineering in Medicine and Biology Society 2012
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/37262
_version_ 1848754998310076416
author Khan, Masood Mehmood
Oz, Ihsan
author2 Yuan-Ting Zhang
author_facet Yuan-Ting Zhang
Khan, Masood Mehmood
Oz, Ihsan
author_sort Khan, Masood Mehmood
building Curtin Institutional Repository
collection Online Access
description Recent works suggest that thermal intensity values (TIVs) measured around the facial thermal feature points (FTFPs) can help in distinguishing between the facial expression of affective states. This work investigates if the average pixel grey-levels, instead of TIVs, measured in sub-image masks around the FTFPs allow classifying facial expressions. Thermal infrared images from the IEEE OTCBVS database were used to distinguish between facial expressions. The pixel grey-levels measured in sub-image masks were used to measure, for each individual, the Euclidean distance between images of different facial expressions. Linear discriminant analysis was performed to obtain hyper-planes for separating the clusters of sample images. Significant pixel grey-level differences were observed at FTFPs between three facial expressions; neutral, happy, and angry. More than 96 of the original images in a three-expression Gaussian mixture model were separable and clustered around distant centroids in a discriminant space.
first_indexed 2025-11-14T08:49:19Z
format Conference Paper
id curtin-20.500.11937-37262
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:49:19Z
publishDate 2012
publisher IEEE Engineering in Medicine and Biology Society
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-372622017-01-30T14:01:11Z Efficacy of Biophysiological Measurements at FTFPs for Facial Expression Classification: A Validation Khan, Masood Mehmood Oz, Ihsan Yuan-Ting Zhang biophysiological signal processing Affective computing affect recognition facial expression classification Recent works suggest that thermal intensity values (TIVs) measured around the facial thermal feature points (FTFPs) can help in distinguishing between the facial expression of affective states. This work investigates if the average pixel grey-levels, instead of TIVs, measured in sub-image masks around the FTFPs allow classifying facial expressions. Thermal infrared images from the IEEE OTCBVS database were used to distinguish between facial expressions. The pixel grey-levels measured in sub-image masks were used to measure, for each individual, the Euclidean distance between images of different facial expressions. Linear discriminant analysis was performed to obtain hyper-planes for separating the clusters of sample images. Significant pixel grey-level differences were observed at FTFPs between three facial expressions; neutral, happy, and angry. More than 96 of the original images in a three-expression Gaussian mixture model were separable and clustered around distant centroids in a discriminant space. 2012 Conference Paper http://hdl.handle.net/20.500.11937/37262 IEEE Engineering in Medicine and Biology Society fulltext
spellingShingle biophysiological signal processing
Affective computing
affect recognition
facial expression classification
Khan, Masood Mehmood
Oz, Ihsan
Efficacy of Biophysiological Measurements at FTFPs for Facial Expression Classification: A Validation
title Efficacy of Biophysiological Measurements at FTFPs for Facial Expression Classification: A Validation
title_full Efficacy of Biophysiological Measurements at FTFPs for Facial Expression Classification: A Validation
title_fullStr Efficacy of Biophysiological Measurements at FTFPs for Facial Expression Classification: A Validation
title_full_unstemmed Efficacy of Biophysiological Measurements at FTFPs for Facial Expression Classification: A Validation
title_short Efficacy of Biophysiological Measurements at FTFPs for Facial Expression Classification: A Validation
title_sort efficacy of biophysiological measurements at ftfps for facial expression classification: a validation
topic biophysiological signal processing
Affective computing
affect recognition
facial expression classification
url http://hdl.handle.net/20.500.11937/37262