IIT Delhi Finger Knuckle Database (Version 1.0)

Finger knuckle recognition has been emerging as the highly convenient biometric with high user acceptance. However, this biometric modality has attracted very little attention from the researchers. In the best of our knowledge, there is no freely available finger knuckle image databases so far in the public domain. The Biometrics Research Laboratory at IIT Delhi has been developing the finger knuckle image database since August 2006. The objective is to establish large scale finger knuckle image database for the research and make it available in the public domain.

Brief Description

The IIT Delhi finger knuckle image database consists of the images acquired from the students and staff at IIT Delhi, New Delhi, India. This database has been acquired in IIT Delhi campus during August 2006 - Jun 2007 using a digital camera. The currently available database is from 158 users, all the images are in bitmap (*.bmp) format. All the subjects in the database are in the age group 16-55 years. This database of 790 images have been sequentially numbered for every user with an integer identification/number. The resolution of these images is 80 ´ 100 pixels and all these images are available in bitmap format.

Sample Images

The entire database as detailed above is made available for the research. The sample images from this database are reproduced in the following image four sets. 





Download and Copyright

The database is being made available for the researchers from November 2007 onwards. Interested researchers should follow following steps to acquire the 'IIT Delhi Finger Knuckle Database version 1.0'


    1. Visit the online application link and provide all the details in this application form;

    2. The request confirmation will be sent by email and the applicants can download the database using instructions in the email.


All the rights of the IIT Delhi Finger Knuckle Database are reserved and commercial use/distribution of this database is strictly prohibited. All the technical reports and papers that report experimental results from this database should provide due acknowledgement and reference. The reference should appear as 'IIT Delhi Finger Knuckle Database version 1.0. Questions regarding this database can be directed to ajaykr@ieee.org.



[1] Ajay Kumar and Yingbo Zhou, “Human Identification using KnuckleCodes”, Proc. BTAS, pp. 147-152, 2009.

[2] Ajay Kumar and Ch. Ravikanth, “Personal authentication using finger knuckle surface, IEEE Trans. Information Forensics & Security, vol. 4, no. 1, pp. 98-110, Mar. 2009 1, pp. 98-110, Mar. 2009.  

Back to Databases Page