Detecting facial expressions using the kinect camera

• Main Author: Kulandaivelu Giridharan
• Other Authors: Justin Dauwels
• Format: Theses and Dissertations
• Language: English
• Published: 2017
• Subjects: DRNTU::Engineering::Electrical and electronic engineering
• Online Access: http://hdl.handle.net/10356/69522
• Institution: Nanyang Technological University

This dissertation reports and recapitulates the progress of author’s research work on “Detecting facial expressions using the Kinect camera” under the scrutiny of Professor Justin Dauwels. This project comprises of the prospect detection of human emotion using Kinect Version 2. In this part, brightness changes in face while heart contracts and expands is used for extraction of features. The latter part of project includes the methods and procedures to process raw data and detect emotions. The prime objective of this project is to initially gather reliable data for heart rate detection using Kinect Version 2. Following which, a well designated protocol shows the subject a blend of YouTube videos to induce different emotions including happy, sad and neutral. Finally, analysis will be performed using heart rate detection algorithms and Tinke to detect the emotion of the subject. In this project, other than Kinect V2, TInke and Wrist blood pressure monitor are used. The prime aim is to pin point the heart rate ranges that can be assigned to emotions and to methodize the use of Kinect V2 to detect the heart rates for each kind of human emotion.