Full metadata record
DC FieldValueLanguage
dc.contributorDepartment of Computingen_US
dc.creatorLi, Wenxin-
dc.identifier.urihttps://theses.lib.polyu.edu.hk/handle/200/87-
dc.languageEnglishen_US
dc.publisherHong Kong Polytechnic University-
dc.rightsAll rights reserveden_US
dc.titleAuthenticating personal identities using palmprint recognitionen_US
dcterms.abstractPalmprint recognition technology is based on the identification of creases, wrinkles, ridges and hollows of the inner surface of the human palm. Palmprint recognition research, especially where it integrates fingerprint and hand geometry, is an area of great promise in the search for ever more reliable personal identity authentication and security systems. Our research over the last five years has made a number of major practical and theoretical contributions to the field of palmprint recognition. Our development of an online capture device has proven the feasibility of using palmprint recognition technology to identify people in real time. Our establishment of a palmprint database (ten thousand images collected from one thousand volunteers) has allowed us to thoroughly test the development of several novel palmprint positioning/segmentation, feature extraction/presentation and matching algorithms. We have proposed three palmprint positioning algorithms based on end points of the heart line and the outer boundary of the palm, on conjunction points between fingers, and on an inscribed circle. For the reference of researchers in the field, we also developed a number of feature extraction and matching methods: texture analysis, Fourier Transform and bi-directional matching of creases. This last proved itself 97.5% accurate and we are working on a new method to improve it. Finally, we also implemented a proof-of-concept palmprint verification system integrated with a smart card. Our publications include eight journal papers and five conference papers with one paper currently under review. In our future work we hope to improve the capture device, develop, test and compare other methods, enlarge our database, and find a way to locate and identify a palmprint in a free-of-scale image. Palmprint recognition shows great promise as a way to authenticate personal identities. With further research it will certainly become an established and accepted technology in the increasingly important fields of security and personal identity authentication.en_US
dcterms.extentiv, 139 leaves : ill. ; 30 cmen_US
dcterms.isPartOfPolyU Electronic Thesesen_US
dcterms.issued2004en_US
dcterms.educationalLevelAll Doctorateen_US
dcterms.educationalLevelPh.D.en_US
dcterms.LCSHHong Kong Polytechnic University -- Dissertationsen_US
dcterms.LCSHBiometric identificationen_US
dcterms.LCSHPalmprintsen_US
dcterms.accessRightsopen accessen_US

Files in This Item:
File Description SizeFormat 
b17726566.pdfFor All Users5.41 MBAdobe PDFView/Open


Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. 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.
  3. 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.

Show simple item record

Please use this identifier to cite or link to this item: https://theses.lib.polyu.edu.hk/handle/200/87