Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Computing | en_US |
| dc.contributor.advisor | Kumar, Ajay (COMP) | - |
| dc.creator | Yu, Tong | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/9405 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | A study on finger knuckle characteristics for forensic applications | en_US |
| dcterms.abstract | More and more biometrics can help us authenticate. Compared with other physiological characteristics, finger knuckle print has its own advantage. For example, finger knuckle print is rich in texture detail and it can be acquired easily. Finger knuckle lines have also been successfully applied in forensic field as an evidence. By observing many peoples' hands, I found similarities in the finger knuckle lines of the same individual's right index finger and middle finger, left and right index finger. Then, I give some features to measure the similarity between two fingers. I used AutoCAD to measure the value of each feature. When I want to find out from a dataset which finger and the known finger are from the same person, I compare their features. A score is used to measure their similarity. If two fingers are similar, the score will be lower. Most of time, we can get a good result. Because of the manual measurements and some of the texture characteristics, sometimes poor results are produced. This report describes a method used to determine whether two finger knuckle patterns are from the same person. Our experimental results illustrate that our approach can be used in the forensic investigation for the personal identification. This report also analyzes reasons for the failure of this approach in some cases. A new function to automatically ascertain the similarity between two knuckle images is proposed which uses unique features such as the curvature of knuckle. The effectiveness of this function is enhanced by incorporating soft features like the skin color or nail characteristics. This report also provides further directions to address the limitations of the approach detailed in this report. | en_US |
| dcterms.extent | vii, 30 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2018 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.LCSH | Biometric identification | en_US |
| dcterms.LCSH | Forensic sciences | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 991022109836703411.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.79 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/200/9405