Noncontact Fingerprint Systems Competition Overview
1. Register by the timeline to participate in the competion (indicate if you wish to be an anonymous
participant).
2. Sign and submit Database License Agreement(form to be sent only after successful registration).
3. Follow instructions for shipping hardware systems.
4. The LivDet team will evaluate the submitted systems.
5. Performance will be assessed.
6. Results to be presented at IJCB 2023.
7. LivDet 2023 System output liveness scores would be made available to researchers after competition.
Release of Training Dataset
Training dataset would not be provided for the LivDet-2023 Noncontact Fingerprint Systems competition category. Competittors may use any publicly available datasets or their proprietory datasets if needed.
Submission Instructions for Noncontact-based Fingerprint Systems
Each submitted system must meet the following parameters:
1. Participants will mail their own noncontact fingerprint system to the address: Dr. Stephanie Schuckers, 8 Clarkson Avenue, Potsdam, NY-13699, USA
2. Installation Requirements:
- Windows 11-64-bit OS or end-to-end complete (eg. mobile) system (with no software that needs to be installed on a desktop)
- All necessary software Modules must be provided:
- .Exe or similar executable only
The submitted system should be able to input the label (letters, numbers and special charecters) of the sample (either single fingertip or four fingers as per system capacity) it is being tested against to keep an account of the corresponding test scores
System output
The system output file format must be a .txt file, with sample labels and corresponding test scores saved after the process of each image presented to the system.
- 1. Collected image from the test samples
- 2. The output score for the processed image (Liveness scores only) - is a posterior probability of the live class given the image or a degree of liveness
normalized in the range 0 and 100 (100 is the maximum degree of liveness, 0 means that the image is fake). In the
case that the system has not been able to process the image, the correspondent output must be -1000 (failure
to enroll).
- 3. The image processing duration (in seconds) - duration required for the data capture subsystem and comparison subsystem to acquire and process a sample, inclusive of PAD subsystem processing duration
Performance Evaluation of Noncontact Fingerprint Systems
Laboratory staff will systematically attempt to evaluate the system with live or spoof data at a time and collect the corresponding performance scores
- Upto 1000 live attempts
- Upto 1000 attempts with different presentation attacks
The parameters adopted for the performance evaluation of each successfully submitted system will be the following:
- Attack presentation classification error rate (APCER): proportion of attack presentations using the same PAI species incorrectly classified as bona fide presentations at the PAD subsystem in a specific scenario
- Bona fide presentation classification error rate (BPCER):
proportion of bona fide presentations incorrectly classified as presentation attacks at the PAD subsystem in a specific scenario
- Attack presentation non-response rate (APNRR):
proportion of attack presentations using the same PAI species that cause no response at the PAD subsystem or data capture subsystem
- Weighted Average of APCER (APCERaverage): average of APCER accross all PAIs, weighted by the sample counts in each PAI category
- Average Classification Error Rate (ACER): average of APCERaverage and BPCER. (Only for the purpose of competition ranking)
- Full system processing duration (FS-PD):
duration required for the data capture subsystem and comparison subsystem to acquire and process a sample, inclusive of PAD subsystem processing duration
- Definitions:
- Presentation Attack (PA): presentation to the biometric data capture subsystem with the goal of interfering with the operation of the biometric system
- Presentation Attack Instrument (PAI)*: biometric characteristic or object used in a presentation attack
- The winner of the systems competition category will be awarded based on minimum overall classification error. One winner will be awarded.
- *In the case here PAI species are the known and unknown spoof recipes that will be used in this competition
Rates are based on the assumption of a threshold
of 50. Quality and match scores will be computed based on the
collected images to support efforts to maintain
fairness between the submitted systems.