Real time vision/sensor based features processing for efficient HCI employing canonical correlation analysis

Ehab H. El-Shazly, Moataz M. Abdelwahab, Atsushi Shimada, Rin-Ichiro Taniguchi

Research output: Contribution to journalArticle

Abstract

In this paper, a global algorithm for facial and gesture recognition is presented. The algorithm basically consists of three modules: features sensing and processing, dominant features selection and finally features matching. Depending on the type of data used (vision or sensor based), the proposed algorithm exploits multiple features employing 2DPCA that efficiently compact features’ descriptors maintain the spatial and temporal alignment of features’ components. Canonical Correlation Analysis (CCA) is employed to fuse different features from different descriptors or different performers. CCA also transforms training and testing features sets into new space where similar pairs become highly correlated pairs. Different experiments were conducted using well known data sets in addition to our newly collected data sets to verify the efficiency of the proposed algorithm. Excellent recognition accuracy, and fast performance are factors that promotes the proposed algorithm for real time implementation.

Original languageEnglish
Pages (from-to)187-195
Number of pages9
JournalJournal of Reliable Intelligent Environments
Volume2
Issue number4
DOIs
Publication statusPublished - Dec 1 2016

Fingerprint

Human computer interaction
Sensors
Processing
Gesture recognition
Electric fuses
Feature extraction
Testing
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science (miscellaneous)
  • Renewable Energy, Sustainability and the Environment

Cite this

Real time vision/sensor based features processing for efficient HCI employing canonical correlation analysis. / El-Shazly, Ehab H.; Abdelwahab, Moataz M.; Shimada, Atsushi; Taniguchi, Rin-Ichiro.

In: Journal of Reliable Intelligent Environments, Vol. 2, No. 4, 01.12.2016, p. 187-195.

Research output: Contribution to journalArticle

@article{b6f66d26ec51439cba7691247e13a924,
title = "Real time vision/sensor based features processing for efficient HCI employing canonical correlation analysis",
abstract = "In this paper, a global algorithm for facial and gesture recognition is presented. The algorithm basically consists of three modules: features sensing and processing, dominant features selection and finally features matching. Depending on the type of data used (vision or sensor based), the proposed algorithm exploits multiple features employing 2DPCA that efficiently compact features’ descriptors maintain the spatial and temporal alignment of features’ components. Canonical Correlation Analysis (CCA) is employed to fuse different features from different descriptors or different performers. CCA also transforms training and testing features sets into new space where similar pairs become highly correlated pairs. Different experiments were conducted using well known data sets in addition to our newly collected data sets to verify the efficiency of the proposed algorithm. Excellent recognition accuracy, and fast performance are factors that promotes the proposed algorithm for real time implementation.",
author = "El-Shazly, {Ehab H.} and Abdelwahab, {Moataz M.} and Atsushi Shimada and Rin-Ichiro Taniguchi",
year = "2016",
month = "12",
day = "1",
doi = "10.1007/s40860-016-0028-4",
language = "English",
volume = "2",
pages = "187--195",
journal = "Journal of Reliable Intelligent Environments",
issn = "2199-4668",
publisher = "Springer International Publishing AG",
number = "4",

}

TY - JOUR

T1 - Real time vision/sensor based features processing for efficient HCI employing canonical correlation analysis

AU - El-Shazly, Ehab H.

AU - Abdelwahab, Moataz M.

AU - Shimada, Atsushi

AU - Taniguchi, Rin-Ichiro

PY - 2016/12/1

Y1 - 2016/12/1

N2 - In this paper, a global algorithm for facial and gesture recognition is presented. The algorithm basically consists of three modules: features sensing and processing, dominant features selection and finally features matching. Depending on the type of data used (vision or sensor based), the proposed algorithm exploits multiple features employing 2DPCA that efficiently compact features’ descriptors maintain the spatial and temporal alignment of features’ components. Canonical Correlation Analysis (CCA) is employed to fuse different features from different descriptors or different performers. CCA also transforms training and testing features sets into new space where similar pairs become highly correlated pairs. Different experiments were conducted using well known data sets in addition to our newly collected data sets to verify the efficiency of the proposed algorithm. Excellent recognition accuracy, and fast performance are factors that promotes the proposed algorithm for real time implementation.

AB - In this paper, a global algorithm for facial and gesture recognition is presented. The algorithm basically consists of three modules: features sensing and processing, dominant features selection and finally features matching. Depending on the type of data used (vision or sensor based), the proposed algorithm exploits multiple features employing 2DPCA that efficiently compact features’ descriptors maintain the spatial and temporal alignment of features’ components. Canonical Correlation Analysis (CCA) is employed to fuse different features from different descriptors or different performers. CCA also transforms training and testing features sets into new space where similar pairs become highly correlated pairs. Different experiments were conducted using well known data sets in addition to our newly collected data sets to verify the efficiency of the proposed algorithm. Excellent recognition accuracy, and fast performance are factors that promotes the proposed algorithm for real time implementation.

UR - http://www.scopus.com/inward/record.url?scp=85065126730&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065126730&partnerID=8YFLogxK

U2 - 10.1007/s40860-016-0028-4

DO - 10.1007/s40860-016-0028-4

M3 - Article

VL - 2

SP - 187

EP - 195

JO - Journal of Reliable Intelligent Environments

JF - Journal of Reliable Intelligent Environments

SN - 2199-4668

IS - 4

ER -