Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Computing | en_US |
| dc.creator | Hu, Jiaxin | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/11371 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Online palmprint detection under complex background | en_US |
| dcterms.abstract | As a highly desirable technology, online contactless palmprint identification can provide higher user convenience in a range of high security applications. Accurate detection of contactless palmprint region of interest is a key step in matching such palmprint images. Therefore, this work attempts to devise more accurate method of contactless palmprint detection for the challenging images that are acquired under complex background, illumination, along with varying pose and scale changes. A range of deep neural network-based object detection frameworks are investigated to accurately detect key points between different fingers on different databases. We finally adapted YOLOv4 as a new detection architecture to be incorporated for the detection of contactless palmprint images. The efficiency and accuracy from different framework, using different evaluation methods, are used to determine effectiveness of such contactless palmprint detector for the real-world applications. A new database of contactless 2D palmprint images is also developed in this work to evaluate the effectiveness from different network for more challenging contactless images. The inter-finger key points, or finger gap points, on all the images in this database have been labelled and are used to extract rotation-invariant palmprint regions. We also use this database to present comparisons with other related contactless palmprint database in the effectiveness of different methods to extract reliably extract the palmprint regions. This report also presents some preliminary attempts to detect 3D palmprint pose from a single contactless 2D palmprint images, and visualizes encouraging results for the further work in this area. | en_US |
| dcterms.extent | ii, 30 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2021 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Biometric identification | en_US |
| dcterms.LCSH | Palmprints | 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 | |
|---|---|---|---|---|
| 5819.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.07 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/200/11371