Machine vision based facial expressions recognition and analysis for Filipino gamers

Date of Publication

2017

Document Type

Master's Thesis

Degree Name

Master of Science in Electronics and Communications Engineering

College

Gokongwei College of Engineering

Department/Unit

Electronics and Communications Engineering

Thesis Adviser

Melvin K. Cabatuan

Defense Panel Chair

Edwin Sybingco

Defense Panel Member

Alexander C. Abad
Cesar A. Llorente

Abstract/Summary

This research investigates the problem of expressions detection and analysis for Filipino gamers. The importance of expressions detection is that they are an advanced form of recognition that may be able to detect far more emotion than standard face tracking could do. These expressions would only last for a range of less than a second, which proves the difficulty of its analysis quite well.

The aim of this Masters thesis is the development of a expression detection and analysis system that in order to understand user emotional response during an actual gameplay. Emotional response is one of the most important factors in video games, as it is a rare form of media that relies on interaction with the audience. The contribution to enhanced satisfaction in video games as well as improvement of interactive game play.

A total of ten participants will be recruited in order to perform the experimentation and data gathering. Data will be collected using expression detection and analysis. Data analysis performed to generate results from questionnaires, psychological analysis, as well machine learning.

This research is limited through the use of Open CV and Python for the coding, limited to the scope of the face for the detection, and limited to only detecting four levels of emotions. The contributions from the work include tools such as a new codebook or dictionary for learning a database of expressions, metrics for measuring performance, and systematic approach for detection.

Abstract Format

html

Language

English

Format

Electronic

Accession Number

CDTG007816

Shelf Location

Archives, The Learning Commons, 12F Henry Sy Sr. Hall

Physical Description

1 computer disc ; 4 3/4 in.

Keywords

Video games--Philippines

This document is currently not available here.

Share

COinS