The First CCBR Competition on Fingerprint Recognition (CCFP2014)
With an increasing emphasis on security, fingerprint based automated personal identification has been receiving extensive attention these years. Although fingerprint recognition is well-known, applications of fingerprint recognition in real world are still challenging tasks for unpredictable variations of fingerprint images. Therefore the first CCBR Competition on Fingerprint Recognition (or CCFP2014 shortly) is organized to track the state-of-the-art of Fingerprint recognition in uncontrolled conditions.
CCFP2014 is open to both academia and industry. There are two fingerprint image databases used in CCFP2014 for training and testing purposes, respectively. The training database (CASIA-FingerprintV5) contains 20,000 fingerprint images of 500 subjects. Each volunteer contributed 40 fingerprint images of his eight fingers (left and right thumb/second/third/fourth finger), i.e. 5 images per finger. The fingerprint images of CASIA-FingerprintV5 were captured using URU4000 fingerprint sensor in one session. All fingerprint images are 8 bit gray-level BMP files and the image resolution is 328×356 (Fig. 1). And the testing database (CASIA-Fingerprint-TestV1) contains 6,000 fingerprint images of 1,200 fingers from 300 subjects. The fingerprint images of CASIA-Fingerprint-TestV1 were captured using URU4000 fingerprint sensor in one session. Each volunteer contributed 20 fingerprint images of both left and right hands (second/third finger), i.e. 5 images each class. The significant intra-class variations in CASIA-Fingerprint-TestV1 are generated by rotation, deformation and so on. All fingerprint images of CASIA-Fingerprint-TestV1 are 8-bit gray-level BMP files and the image resolution is 328*356 (Fig. 2).
Fig. 1 Example Fingerprint images in the training database
Fig. 2 Example Fingerprint images in the testing database
All participants should submit two executables "fpenroll_AlgorithmName.exe" and "fpmatch_AlgorithmName.exe" in the form of Win64 console applications for third-party performance evaluation. The file "fpenroll_AlgorithmName.exe" is used to generate a feature template from a fingerprint image. The file "fpmatch_AlgorithmName.exe" is used to match two fingerprint feature templates. The syntax of the two executables through command-line is as follows.
>fpenroll_AlgorithmName imagefile templatefile outputfile
> fpmatch_AlgorithmName templatefile1 templatefile2 outputfile
All possible intra-class comparisons are implemented to evaluate the false non-match rate (FNMR) providing a total of 12,000 intra-class match results. One sample is selected from each fingerprint class to evaluate the false match rate (FMR) so there are totally 719,400 inter-class match results. If an intra- or inter-class comparison cannot be successfully implemented due to failure enrollment or failure match, a random variable ranging from 0 to 1 will be assigned as the matching score. Popular performance metrics of fingerprint recognition such as FNMR, FMR, EER and ROC will be reported and the metric F4(FNMR@ FMR=0.0001) will be used to rank the performance of submitted algorithms.
Each participant can maximally submit three algorithms. We only accept qualified Fingerprint recognition algorithms which meet the following requirements due to limited competition resources:
• The equal error rate (EER) must be less than 10% on the training database.
• The average processing time for feature encoding must be less than 3 seconds and the average matching time must be less than 0.1 second on a normal personal computer.
A public platform, the Biometrics Ideal Test (BIT; http://biometrics.idealtest.org) is used to organize the competition. The competition registration process is as follows.
1. Register an account in BIT (http://biometrics.idealtest.org ) and select the option "Participant of CCBR Competition on Fingerprint Recognition".
2. Download the training database CASIA-FingerprintV5 after your account is approved and activated.
3. Develop a fingerprint recognition algorithm and you can use the CASIA-FingerprintV5 or other fingerprint image databases as the training data.
4. Submit your algorithm to firstname.lastname@example.org. If size of the algorithm file is too large, you can also send us a web link for download. To help users quickly master the programming protocols of algorithm evaluation, the source codes of the example files "enroll.c" and "match.c" are provided for download as below. Download C language source code here
5. Any problem of your algorithm during testing will be reported to you so please respond immediately to the organizers of CCFP2014.
6. The CCFP2014 Competition Committee will report the performance of all submitted algorithms and the competition results.
7. Authors of the winner algorithm will be invited to write a paper on their algorithm to be published in the CCBR2014 proceedings.
Any questions on CCFP2014 can be addressed by emailing email@example.com.
Open of the competition April 1, 2014
Deadline of algorithm submission June 30, 2014
Release of the testing results During the CCBR2014