Geometrical modeling of facial regions and CUDA based parallel face segmentation for emotion recognition

Sabu George

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Human emotions are expressed through body gestures, voice variations and facial expressions. Research in the area of facial expression recognition has been active for last 20 years for improving the system performance. This work proposes a novel geometrical modeling of facial regions based feature extraction technique for emotion recognition. Most of the facial landmark based approaches use a common reference point for detecting the facial variations. In such approaches a slight variation or tripping of the reference point may result in errors which may lead to erroneous expression recognition. In order to reduce errors a new method is proposed wherein 3 important reference points in the axis of symmetry of face is fixed and angle variations associated with these reference points are used for detecting the upper and lower Action Units (AUs). Also to increase the speed performance the segmentation algorithm required for facial feature extraction is implemented parallel in Compute Unified Device Architecture (CUDA). Facial expressions of emotion are recognised as combinations of FACS AUs. It is implemented in Graphics Processing Unit (GPU) based High Performance Computing (HPC), tesla K20, CUDA server and analysed the performance as a massively parallel data processing tool. The results showed that multithreaded GPU version of the face segmentation algorithm is much faster than that of single-threaded CPU version.

Original languageEnglish
Pages (from-to)6740-6752
Number of pages13
JournalInternational Journal of Applied Engineering Research
Volume11
Issue number9
Publication statusPublished - 01-01-2016
Externally publishedYes

Fingerprint

Feature extraction
Program processors
Servers
Graphics processing unit

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

@article{55fa84b3adda451898b44fe67ea489cd,
title = "Geometrical modeling of facial regions and CUDA based parallel face segmentation for emotion recognition",
abstract = "Human emotions are expressed through body gestures, voice variations and facial expressions. Research in the area of facial expression recognition has been active for last 20 years for improving the system performance. This work proposes a novel geometrical modeling of facial regions based feature extraction technique for emotion recognition. Most of the facial landmark based approaches use a common reference point for detecting the facial variations. In such approaches a slight variation or tripping of the reference point may result in errors which may lead to erroneous expression recognition. In order to reduce errors a new method is proposed wherein 3 important reference points in the axis of symmetry of face is fixed and angle variations associated with these reference points are used for detecting the upper and lower Action Units (AUs). Also to increase the speed performance the segmentation algorithm required for facial feature extraction is implemented parallel in Compute Unified Device Architecture (CUDA). Facial expressions of emotion are recognised as combinations of FACS AUs. It is implemented in Graphics Processing Unit (GPU) based High Performance Computing (HPC), tesla K20, CUDA server and analysed the performance as a massively parallel data processing tool. The results showed that multithreaded GPU version of the face segmentation algorithm is much faster than that of single-threaded CPU version.",
author = "Sabu George",
year = "2016",
month = "1",
day = "1",
language = "English",
volume = "11",
pages = "6740--6752",
journal = "International Journal of Applied Engineering Research",
issn = "0973-4562",
publisher = "Research India Publications",
number = "9",

}

Geometrical modeling of facial regions and CUDA based parallel face segmentation for emotion recognition. / George, Sabu.

In: International Journal of Applied Engineering Research, Vol. 11, No. 9, 01.01.2016, p. 6740-6752.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Geometrical modeling of facial regions and CUDA based parallel face segmentation for emotion recognition

AU - George, Sabu

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Human emotions are expressed through body gestures, voice variations and facial expressions. Research in the area of facial expression recognition has been active for last 20 years for improving the system performance. This work proposes a novel geometrical modeling of facial regions based feature extraction technique for emotion recognition. Most of the facial landmark based approaches use a common reference point for detecting the facial variations. In such approaches a slight variation or tripping of the reference point may result in errors which may lead to erroneous expression recognition. In order to reduce errors a new method is proposed wherein 3 important reference points in the axis of symmetry of face is fixed and angle variations associated with these reference points are used for detecting the upper and lower Action Units (AUs). Also to increase the speed performance the segmentation algorithm required for facial feature extraction is implemented parallel in Compute Unified Device Architecture (CUDA). Facial expressions of emotion are recognised as combinations of FACS AUs. It is implemented in Graphics Processing Unit (GPU) based High Performance Computing (HPC), tesla K20, CUDA server and analysed the performance as a massively parallel data processing tool. The results showed that multithreaded GPU version of the face segmentation algorithm is much faster than that of single-threaded CPU version.

AB - Human emotions are expressed through body gestures, voice variations and facial expressions. Research in the area of facial expression recognition has been active for last 20 years for improving the system performance. This work proposes a novel geometrical modeling of facial regions based feature extraction technique for emotion recognition. Most of the facial landmark based approaches use a common reference point for detecting the facial variations. In such approaches a slight variation or tripping of the reference point may result in errors which may lead to erroneous expression recognition. In order to reduce errors a new method is proposed wherein 3 important reference points in the axis of symmetry of face is fixed and angle variations associated with these reference points are used for detecting the upper and lower Action Units (AUs). Also to increase the speed performance the segmentation algorithm required for facial feature extraction is implemented parallel in Compute Unified Device Architecture (CUDA). Facial expressions of emotion are recognised as combinations of FACS AUs. It is implemented in Graphics Processing Unit (GPU) based High Performance Computing (HPC), tesla K20, CUDA server and analysed the performance as a massively parallel data processing tool. The results showed that multithreaded GPU version of the face segmentation algorithm is much faster than that of single-threaded CPU version.

UR - http://www.scopus.com/inward/record.url?scp=85026754433&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026754433&partnerID=8YFLogxK

M3 - Article

VL - 11

SP - 6740

EP - 6752

JO - International Journal of Applied Engineering Research

JF - International Journal of Applied Engineering Research

SN - 0973-4562

IS - 9

ER -