Welcome to the upgraded BRAC University Institutional Repository. We are currently organizing collections after a recent system upgrade. Homepage category counters may temporarily show lower numbers while syncing, but over 27,000 repository items remain safe and accessible. Please use the search bar to find theses, scholarly outputs, and institutional documents.

Study on human emotion based on facial expressions through human machine communication

Citation

Abstract

Facial expressions are reactions of internal emotions that express states of human minds. In busy life people are ignorant about the emotions of others. Sometimes it’s hard for a person to interact with another individual by understanding their mental condition. As a result, accidents, violent events, misunderstandings and even rates of divorce are raised across the world. But computers can be a source of relief in anger management, depression assessment or simply sharing joy. Using the projections of feelings from facial surface by mainly observing the unusual movements of nose, lips, eyes, cheeks etc. through a camera for detection of proper emotion to begin a communication between a human and a machine mainly to help the end user to get out of distress or to amplify inner positivity. Our study tends to use the methodologies of machine learning, data science, image processing and several other applied processes of these to perceive and analyze the responses of facial aspects to meet the expected outcome. Several studies have taken place considering this particular physical fatigue but none has expressed an approach to help people psychologically neither at work places or at places where they accommodate where our study is a step towards tomorrow for a more realistic interaction between machines and humans.

Description

Cataloged from PDF version of thesis.
Includes bibliographical references (pages 33-36).
This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2020.

Publisher Link

Type

Thesis