Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Faculty of Engineering | en_US |
| dc.creator | Qu, Tong | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/7117 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Low-resolution face recognition | en_US |
| dcterms.abstract | Among face-recognition (FR) problems, the identification of low-resolution (LR) face images is still a challenging task. Traditional FR algorithms cannot work satisfactorily in matching LR probe images to high-resolution (HR) gallery images. To perform this matching, there are three standard approaches: (1) down-sample the gallery images and then perform the matching of LR face images; (2) upscale the probe images using super-resolution (SR) methods and then perform the matching of HR face images; and (3) project the LR probe images and the HR gallery images into a common subspace and then perform matching in the subspace. In this project, traditional algorithms based on the first two approaches will first be introduced and evaluated under different resolutions. The four baseline FR algorithms are PCA, also known as eigenfaces, combined PCA and LDA (PCA+LDA, a variant of fisherfaces), the PCA+LDA-based FR algorithm based on Gabor features (G-PCA+LDA), and LGBPHS. The three baseline SR algorithms are the bicubic interpolation, eigentransformation and Coherent Local Linear Reconstruction Super-resolution (CLLR-SR). After that, a coupled-projection method based on Canonical Correlation Analysis (CCA) is proposed and evaluated. Experiments show that the coupled-projection method produces higher identification rates than other FR methods do. | en_US |
| dcterms.extent | x, 88 p. : ill. ; 30 cm. | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2013 | 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 | |
|---|---|---|---|---|
| b26443107.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.82 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/200/7117