Real-time analytics of two-person dialogues

• Main Author: Lau, Rachael Li Yi
• Other Authors: Justin Dauwels
• Format: Final Year Project
• Language: English
• Published: 2018
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• Online Access: http://hdl.handle.net/10356/75127
• Institution: Nanyang Technological University

In recent years, there has been much progress and advancement to technology in the aspect of deep learning and machine learning. Technology plays a huge part in everyone’s lives in the 21st century. It has evolved in a way that not only benefitted and made living easier and more efficient, but it has also benefitted greatly in the field of medicine and diagnosis. In this paper, a great amount of focus is put into assisting the diagnosis of schizophrenic patients through the use of trained datasets. Schizophrenic patients have been known to exhibit unusual and unique behaviours that differ from healthy humans. The paper will look at the main differences in the two groups’ behaviours to enable easier detection and diagnosis. The primary focus would first be the tracking and detecting the faces and its facial landmarks, through the use of trained models from libraries available. The author has tested and attempted to use different libraries and computing languages to achieve this. The computing languages explored include MATLAB and Python. The libraries explored are OpenCV and dlib.