A Facial Expression Emotion Detection using Gabor Filter and Principal Component Analysis to identify Teaching Pedagogy

Facial expression emotion detection is a challenging and complex field being used in various purposes and contexts. Majority of the existing studies used the JAFEE and Conh-Kanade databases to test the recognition accuracy. Therefore, this study aims to build a Filipino-based facial feature pattern databases based on seven emotions: happy, fear, disgust, neutral, surprised, sad and anger – comprising a total of 611 facial feature patterns validated by experts. The said features were utilized in coming up with the most appropriate teaching pedagogies for educators to provide relevant interventions based on the emotions observed in the class. The study applied SVM with an average classification accuracy of 80.11%, Haar-Cascade Classifier for face detection, Gabor Filter for face extraction, and Eigenfaces API with PCA for recognition. The developed prototype in this study was built in Java, which then performed the five testing experiments that acquired an average accuracy of 43.31% and a highest accuracy of 54.54%. The resulted performance from the experiments considered the variances of the face angle, distance, resolution, lighting condition, and datasets representation patterns.

[1]  W. Reisel,et al.  Primal Leadership: Realizing the Power of Emotional Intelligence , 2016 .

[2]  Stefan Wermter,et al.  Face expression recognition with a 2-channel Convolutional Neural Network , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[3]  S. Leshem,et al.  Teachers’ emotional intelligence : the impact of training , 2016 .

[4]  L. Mangurian.  Learning, Emotion, and their Application for Teaching , 2007 .

[5]  Inquiry-Based Learning in Teacher Education: A Primary Humanities Example. , 2015 .

[6]  D. S. Chaudhari,et al.  Human emotions recognition using adaptive sublayer compensation and various feature extraction mechanisms , 2016, 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET).

[7]  Jonathon Shlens,et al.  A Tutorial on Principal Component Analysis , 2014, ArXiv.

[8]  Lindsay I. Smith,et al.  A tutorial on Principal Components Analysis , 2002 .

[9]  Brian Knutson,et al.  FACIAL EXPRESSIONS OF EMOTION INTERPERSONAL TRAIT INFERENCES , 1996 .

[10]  Rashed Mustafa,et al.  Obscenity Detection Using Haar-Like Features and Gentle Adaboost Classifier , 2014, TheScientificWorldJournal.

[11]  Y. Kimura.  Expressing Emotions in Teaching : Inducement, Suppression, and Disclosure as Caring Profession , 2010 .

[12]  Asma Malik,et al.  A Survey on Facial Expression Recognition Technology and Its Use in Virtual Systems , 2015 .

[13]  Bhupendra Singh,et al.  FACE DETECTION BY HAAR CASCADE CLASSIFIER WITH SIMPLE AND COMPLEX BACKGROUNDS IMAGES USING OPENCV IMPLEMENTATION , 2013 .

[14]  D. Rodrigo-Ruiz,et al.  Effect of Teachers ’ Emotions on Their Students : Some Evidence , 2016 .