The Hong Kong Polytechnic University Contactless Finger Knuckle Images Database (Version 3.0)
There has been increasing interest in studying finger knuckle patterns to establish human identity in wide range of commercial and forensic applications. Prior efforts have however focused on evaluating major finger knuckle which are formed on the finger dorsal surface joining proximal phalanx and middle phalanx bones. This database is established to investigate the possible use of ‘minor’ finger knuckle patterns which are formed on the finger surface joining distal phalanx and middle phalanx bones. The ‘minor’ finger knuckle patterns can either be used as independent biometric patterns or employed to improve the performance from the major finger knuckle patterns. The objective in this work has been to establish a large scale (over 200 different people) knuckle image database for the research and make it available in the public domain to help initiate research efforts in comparing, exploring relationship and combining both knuckle patterns which can often be extracted simultaneously.
The Hong Kong Polytechnic University contactless finger knuckle images database (Version 3.0) is contributed from the male and female volunteers. This database has been largely acquired in The Hong Kong Polytechnic University campus and IIT Delhi Campus during 2006-2013 using a contactless setup that simply uses a hand held camera. This database has 1950 finger knuckle images from the index finger of 221 subjects, all the images are in .JPG format. This database also provides two session finger knuckle images acquired after very long interval (4 to 7 years) to ascertain stability of knuckle crease and curved lines. Besides, this database also includes segmented finger knuckle images, contrast-enhanced images and center point information of every finger knuckle images used for segmentation to extract a normalized region.
The entire database as detailed above is made available for the research. The sample images from this database from two different subjects are reproduced in the following set.
Download and Copyright
This database is now publicly available for the researchers. Interested researchers should follow following steps to acquire "The Hong Kong Polytechnic University Contactless Finger Knuckle Images Database (Version 3.0)’
1. Visit the online application link and provide all the details in this online application form. Please make sure you have read terms and conditions for the database usage ;
2. You will receive automated acknowledgement for the submission of your application.
3. The confirmation of your request will be sent to you by email (normally within one week). Successful applicants can download the database using instructions in thie email.
 A. Kumar, 'Toward pose invariant and completely contactless finger knuckle recognition,' IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 1, no. 3, pp. 201-209, July 2019.
 A. Kumar, 'Contactless finger knuckle authentication under severe pose deformations,' Proc. 8th Intl. Workshop Biometrics & Forensics, Porto, Portugal April 2020.
Back to Databases Page