VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/506| Title: | Advanced methods for face recognition | Authors: | Nguyen Gia Khanh | Keywords: | Face recognition;Eigenface method;Principal component analysis (PCA) | Issue Date: | 2018 | Publisher: | Vietnamese-German University | Abstract: | This thesis presents two popular techniques for detecting and recognizing of human faces which is totally able to setup and implement in real-time face recognition system. They could be used to identify a face of an object, determine if that is a human face or not and recognize the person by comparing main characteristics of his/her face to images of known people in the database. The main idea shared by these algorithms is that a face would be processed as a two-dimensional mathematical matrix before passing through some calculations to find its main features. All faces images are then projected on the feature space (“face space”) to find the corresponding coordinators. The face space is composed of “Eigenfaces” or “Fisherfaces” which are actually eigenvectors found after doing a matrix composition - Eigendecomposition. At the heart of Eigenface method is the Principal Component Analysis (PCA) - one of the most popular unsupervised learning algorithms - while Fisherface is a better version of the previous one which makes use of both Principal Component Analysis and Linear Discrimination Analysis (LDA) to get more reliable results. Both methods would be examined deeply in their working principles as well as their potential applications in reality before coming to conclusion about the advantage and drawback of each one. The algorithms were realized by Python 3.7 with a Graphical User Interface (GUI). Given initial images in the database, the program can detect and recognize the human faces in the provided pictures before saving them in the database to improve the calculation accuracy in the future. After evaluation, the recognition general results are exported on the screen with details included in the text files. This thesis consists of four main parts: 1. Introduction to Face Recognition. 2. Eigenface Method. 3. Fisherface Method. 4. Implementation and Evaluation. |
URI(1): | http://epub.vgu.edu.vn/handle/dlibvgu/506 | Rights: | Attribution-NonCommercial 4.0 International |
| Appears in Collections: | Electrical Engineering and Information Technology (EEIT) |
Files in This Item:
| File | Description | Size | Format | Existing users please Login |
|---|---|---|---|---|
| Advanced methods for face recognition.pdf | 3.67 MB | Adobe PDF |
Page view(s)
103
checked on Oct 16, 2025
Download(s)
30
checked on Oct 16, 2025
Google ScholarTM
Check
This item is licensed under a Creative Commons License