Dissertation/Thesis Abstract

An image-based facial expression recognition system using LDA classifier
by Patel, Milan D., M.S., California State University, Long Beach, 2016, 54; 10196292
Abstract (Summary)

The current project presents the development and implementation of a Facial Expression Recognition (FER) system for detecting expressions such as happiness, anger, sadness, fear, disgust, and surprise from a grayscale image. The system is implemented in MATLAB using the Gabor filter for feature extraction and the Linear Discriminant Analysis method for classification. The system has been extensively tested and evaluated using images from the Japanese Female Facial Expression (JAFFE) database and from the Cohn-Kanade (CK) database. Testing results show that depending on the expression to be detected, the success rate of the system can be as high as 95% for images coming from the JAFFE database, or as high as 80% for images coming from the CK database.

Indexing (document details)
Advisor: Chassiakos, Anastasios
Commitee: Tran, Boi, Yeh, Hen-Geul
School: California State University, Long Beach
Department: Electrical Engineering
School Location: United States -- California
Source: MAI 56/02M(E), Masters Abstracts International
Source Type: DISSERTATION
Subjects: Electrical engineering
Keywords:
Publication Number: 10196292
ISBN: 978-1-369-33937-6
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest