Back close

Geometrical approach for emotion recognition from facial expressions using 4D videos and analysis on feature-classifier combination

Publication Type : Journal Article

Publisher : International Journal of Intelligent Engineering and Systems

Source : International Journal of Intelligent Engineering and Systems, Intelligent Network and Systems Society, Volume 10, Number 2, p.30-39 (2017)

Url : https://www.scopus.com/inward/record.uri?eid=2-s2.0-85016123209&doi=10.22266%2fijies2017.0430.04&partnerID=40&md5=dea2c7bf020fcf7c3282d1e06fd5d835

Campus : Bengaluru

School : Department of Computer Science and Engineering, School of Engineering

Department : Computer Science, Electronics and Communication

Year : 2017

Abstract : Emotion recognition from facial expressions using videos is important in human computer communication where the continuous changes in face movements need to be recognized efficiently. In this paper, a method using the geometrical based approach for feature extraction and recognition of six basic emotions has been proposed which is named as GAFCI (Geometrical Approach for Feature Classifier Identification). Various classifiers, Support Vector Machine (SVM), Random Forest, Naïve Bayes and Neural Networks are used for classification, and the performances of all the chosen classifiers are compared. Out of the 83 feature points provided in the BU4DFE database, optimum feature points are identified by experimenting with several sets of feature points. Suitable feature-classifier combination has been obtained by varying the number of feature points, classifier parameters, and training and test samples. A detailed analysis on the feature points and classifiers has been performed to learn the relationship between distance parameters and classification of emotions. The results are compared with literature and found to be encouraging.

Cite this Research Publication : Dr. Suja P. and Dr. Shikha Tripathi, “Geometrical approach for emotion recognition from facial expressions using 4D videos and analysis on feature-classifier combination”, International Journal of Intelligent Engineering and Systems, vol. 10, pp. 30-39, 2017.

Admissions Apply Now