Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Multi-disciplinary Studies | en_US |
| dc.contributor | Department of Electronic Engineering | en_US |
| dc.creator | Lau, Tse-yim | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/2839 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Face recognition by eigenfaces approach | en_US |
| dcterms.abstract | We have developed a real-time computer system that can recognize a person by comparing characteristics of the face to those of known individuals. Besides, the system can tackle the problem caused by illumination and scaling. Our approach treats the face recognition problem as an intrinsically two-dimensional (2-D) recognition problem rather than requiring recovery of three-dimensional geometry, taking advantage of the fact that faces are normally upright and thus may be described by a small set of 2-D characteristic views. The system functions by projecting face images onto a feature space that spans the significant variations among known face images. The significant features are known as "eigenfaces', because they are the eigenvectors (principal components) of a set of training faces; they do not necessarily correspond to features such as eyes, ears, and noses. The projection operation characterizes an individual face by a weighted sum of the eigenface features, and hence recognizing a particular face is equivalent to comparing these weights to those of known individuals. In order to solve the problem of various illumination directions, we apply both the intra- and inter-face illumination normalization algorithm to compensate the effect due to different angles of lighting source such that the accuracy of recognition will not be seriously affected. The system will select at most the three most similar faces in a face database to an input face. Besides, a general interpolation-scaling algorithm has been added to the system in order to handle numerous scales of images. Some particular advantages of our approach are that it provides for the ability to learn and later recognize new faces in an unsupervised manner, and that it is easy to implement using neural network architecture. | en_US |
| dcterms.extent | 49 leaves : ill. ; 30 cm | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 1999 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Human face recognition (Computer science) | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b14792631.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 2.16 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/2839