Big Data Technologies and Applications. 8th International Conference, BDTA 2017, Gwangju, South Korea, November 23–24, 2017, Proceedings

Research Article

Face Expression Extraction Using Eigenfaces, Fisherfaces and Local Binary Pattern Histogram Towards Predictive Analysis of Students Emotion in Programming

Download
208 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-98752-1_5,
        author={Anna Ramos and Jerico Flor and Michael Casabuena and Jheanel Estrada},
        title={Face Expression Extraction Using Eigenfaces, Fisherfaces and Local Binary Pattern Histogram Towards Predictive Analysis of Students Emotion in Programming},
        proceedings={Big Data Technologies and Applications. 8th International Conference, BDTA 2017, Gwangju, South Korea, November 23--24, 2017, Proceedings},
        proceedings_a={BDTA},
        year={2018},
        month={11},
        keywords={Facial expression Emotion Predictive analysis},
        doi={10.1007/978-3-319-98752-1_5}
    }
    
  • Anna Ramos
    Jerico Flor
    Michael Casabuena
    Jheanel Estrada
    Year: 2018
    Face Expression Extraction Using Eigenfaces, Fisherfaces and Local Binary Pattern Histogram Towards Predictive Analysis of Students Emotion in Programming
    BDTA
    Springer
    DOI: 10.1007/978-3-319-98752-1_5
Anna Ramos1,*, Jerico Flor2,*, Michael Casabuena2,*, Jheanel Estrada2,*
  • 1: Saint Michael’s College of Laguna
  • 2: Technological Institute of the Philippines
*Contact email: annakingramos@yahoo.com.ph, flor.jerico.m@gmail.com, mmcasabuena@firstasia.edu.ph, jheanelestrada29@gmail.com

Abstract

Emotion plays an important role to assess individual reaction and responses depends on the degree of encounter, scenario and experience. In this paper, the study examines the emotions of the five (5) randomly selected students according to the Basic Emotions and Non-Basic Emotions while performing their Java Programming activity task. The study utilized RaspberryPi and Smartphone to capture an image, OpenCV application to analyze the image and application of algorithms: the Fisherfaces, Local Binary Pattern Histogram and Eigenfaces to determine the most like emotion. In this study, the Fisherfaces algorithm showed the highest average accuracy rate of 47.93% among the algorithms. Specifically marked an emotion of “happy and surprise” with accuracy rate of 100% which means that the students perform the activity with knowledge and skills. This result can be used by the experts to consider the emotion as part of assessment hence it may also serve as a tool for effective decision making.