| Author: | Lau, King-ho |
| Title: | Human facial image synthetic system |
| Degree: | M.Sc. |
| Year: | 2006 |
| Subject: | Hong Kong Polytechnic University -- Dissertations Human face recognition (Computer science) Image processing |
| Department: | Department of Computing |
| Pages: | 79 leaves : ill. ; 31 cm |
| Language: | English |
| Abstract: | Human facial image synthesis system allows the generation of near-photographic quality images of faces. It makes use of genetic algorithm to recombine the principal components of human faces images in response to user selection. This process is iterated through a number of generations, gradually getting closer to the target face. This purposed system is applicable for suspect identification, different to the traditional facial feature composition method, it describes the generated face images as a whole, and such that matches the way of human faces identification. It explains an image in terms of a set of model parameters, shapes and texture information. With the facial image database, we are able to synthesise a very close approximation to the target object by using image morphing technique. Therefore the process of facial image synthesis will become a combination and searching procedure, by using the Interactive genetic algorithm with user fitness rating, the prototype system will randomly generated face image and eventually converge to the user target. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b20809050.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 20.02 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/200/2896