Wild Fingerphoto Dataset

The Wild Fingerphoto Dataset (WFD) was collected in wild capture scenarios designed to reflect real-life conditions of self-enrollment, where participants were asked to capture fingerphoto images using their own smartphones. To the best of our knowledge, this is the first dataset collected under such diverse and uncontrolled conditions, encompassing both environmental and device variations.  The WFD dataset consists of 101 unique participants, with each individual capturing images of six fingers: the index, middle, and ring fingers from both the right and left hands, resulting in 101 × 6 = 606 unique identities. The participants range in age from 21 to 65 years, and their skin tones are characterized using the Von Luschan Scale. Out of 101 unique data subjects 40 subjects are female and the remaining are male.  For each finger per subject, 10 samples were captured across two sessions, with a time gap of 2-7 days, in a variety of random environmental settings, including both indoor and outdoor conditions with significant lighting variations. Since participants used their own smartphones for data capture, the WFD dataset included fingerphoto samples from 42 different smartphones with varying imaging resolutions. Figure 6 illustrates examples of fingerphotos collected under various environmental conditions, showcasing the diversity and complexity of the dataset. The WFD dataset includes presentation attack samples generated using three distinct PAIs, carefully chosen to reflect realistic spoofing scenarios. For attack sample generation, one bona fide sample per unique identity was selected, and an iPhone 16 Pro was used as the capturing device. The PAIs employed in this work are:

Computer Screen Display: Bona fide samples were displayed on a high-resolution computer screen and subsequently recaptured using the iPhone 16 Pro.

Smartphone Display: An iPhone 13 Pro was used to display the bona fide samples, which were then recaptured using the same device to simulate a smartphone spoofing attack.

Print Attack: Bona fide samples are printed using a high-quality color laser printer and then recaptured to simulate a printed spoofing attack. The final WFD dataset comprises 606 × 10 = 6060 bona fide samples and 606 × 3 = 1818 attack samples, providing a robust and diverse dataset for evaluating presentation attack detection methods.

Following figure shows examples of fingerphoto samples under various environmental capture conditions. 

Following table summarizes the Presentation Attack Instruments (PAIs) statistics of the newly collected dataset 

Examples of fingerphoto samples and their corresponding attack variants from the WFD dataset. 

Copyright of WFD :

Researcher can avail Wild Fingerphoto Dataset (WFD) by following the procedure mentioned: 

• Researchers are required to send the request to use WFD by sending a copy of the license agreement, completely filled, to vetrekarnarayan@unigoa.ac.in with the subject line "License agreement for Wild Fingerphoto Dataset". 

Note: The license agreement has to be signed by the researcher or supervisor and the signature of a legal authority on behalf of the institution, such as the Head of the institution or Registrar, along with the institutional seal (Rubber Stamp).  The license agreement should be on the researchers institutional letterhead. 

The request will not be considered if due procedures are not followed.  

• Every request to avail WFD will be placed before the Ethical Committee of the Institute for approval, and the confirmation of the request will be sent via email. Further, all the instructions related to access to the database will be detailed in the email.

This database is available only for research and educational purposes and not for any commercial use. Further, the use of the database is only for one year from the date of signing the agreement by the researcher. Beyond the allocated one year for the usage of data, the applicant has to apply again following the due procedure.  

The database is available only for research and educational purposes. All the rights of the Wild Fingerphoto Dataset (WFD) 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. If you use the database in any publications or reports, you must refer to the following paper:  

• Hailin Li, Raghavendra Ramachandra, Narayan Vetrekar, R. S. Gad, Diffusion Model with Perceptual Similarity fusion for Unsupervised Fingerphoto Presentation Attack Detection, IEEE Transaction on Biometrics, Behavior, and Identity Science (T-BIOM) – Paper under review.