The KTU CVPR Lab. Palmprint Database-2 contains 15440 color images corresponding to 534 different palms in BMP image format. In that, 6408 images were used as training set, and 9032 images were also used as test set. The images in the database is collected with a novel online palmprint verification system mounted to a student laboratory entrance in 1 year period. Each image in the database was taken using low cost CCD camera with resolutions 768 x 576 pixels at 75 dpi.

Number of the samples per individual in the database were restricted between 13 and 40. Since the images were taken in different sessions some variations were appeared in the images, like focus, illuminations, and pose of the hand. The users have automatically been guided by the system in both the enrolment and testing stages. This gives us an opportunity to have a palmprint database contains palm images collected from the real environment within the real life conditions.

The palmprint images in the database are labeled as "G_xxx_T_yy.bmp", where "G" is the index of the image's group ('R' indicates the reference (train), 'T' indicates the test image), the "xxx" is the unique palm identifier (range from 001 to 534), "T" is the index of the type of the image ('F' indicates the full palm image while 'P' indicates the palmprint image (ROI)) and "yy" is the index of each palm.

All rights of the KTU CVPR Lab. Palmprint Database-2 are reserved. The database is only available for research and noncommercial purposes. Commercial distribution or any act related to commercial use of this database is strictly prohibited. All public work based on the KTU CVPR Lab. Palmprint Database-2 should clearly and prominently carry the following acknowledgement:

"Portions of the work were tested on the KTU CVPR Lab. Palmprint Database-2."

A citation to "KTU CVPR Lab. Palmprint Database-2, http: //ceng2.ktu.edu.tr/~cvpr/palmDB2.htm" must also be added in the references. A soft copy of any released or public documents that use the KTU CVPR Lab. Palmprint Database-2 must be forwarded immediately to: ekinci@ktu.edu.tr

This database is made publicly available and can be obtained from this website. It is totally free for academic, noncommercial purposes. Any person or organization that wishes to use the database must agree to the terms of the agreement and fill in the agreement forms. The request confirmation will be sent by an email and the successful applicants will receive their login accounts and passwords to download the database.

Application Form

Computer Vision and Pattern Recognition Lab.
Karadeniz Technical University
Trabzon, TURKEY
E-mail: ekinci@ktu.edu.tr