Instructions for Participants



Each participant is invited to submit its own algorithm in a Win32 console application. The performance will be evaluated by utilizing a very large data set of fingerprint images captured with an optical scanner (Microsoft® Fingerprint Reader – model 1033). The binary file should open all the .bmp files contained in a specific folder indicated by the user, and output a results.txt file with each line containing the information of the detected singular points for each image file, as in the following example:

!,0000.bmp,?
!,0001.bmp,C Xc Yc,C Xc Yc,D Xd Yd,?

 where (Xc,Yc) and (Xd,Yd) represent the pixels coordinates of the detected cores and deltas, respectively.
The first line in the example reports a case where no singular points were detected in image 0000.bmp, while the second line reports a case where two cores and one delta were detected in image 0001.bmp.
(for a more detailed example, please refer to the training database annotation file)

The participants should briefly indicate how to run the submitted software.

The evaluation will be based on measures that will consider the quantity and type of the detected singular points as well as their distance to the ground truth, which will be manually labeled beforehand. For a ground truth singular point, (x0;y0;t0), if a detected singular point (x;y;t), satisfies (t=t0) and sqrt((x-x0)^2+(y-y0)^2)<10, it is said to be truly detected and, otherwise, it is called a miss.
  • The detection rate is defined as the ratio of truly detected singular points to all ground truth singular points.
  • The miss rate is defined as the ratio of the number of missed singular points to the number of all ground truth singular points.
  • The false alarm rate is defined as the number of falsely detected singular points versus the number of all ground truth singular points.
  • If all singular points are detected and there are no spurious singular points in a fingerprint, the fingerprint is considered to be “correctly” detected.
The performance rank will be compiled and published in this site and will be based on the percentage of correctly detected fingerprints. The average distance error of the correctly detected singular points to the ground truth will be used in the cases where ties occur.

The best algorithm will win the "Best Fingerprint Singular Points Detection Algorithm Award" at ICIAR 2010. A Special Session will be devoted to present and discuss the experimental results of the best algorithms (up to five). The authors of the best algorithms will be invited to submit a paper to the conference (more info).

The goal of the competition is to compare different methodologies for software-based fingerprint singular points detection within a data set composed by real fingerprint images. The ambition of the competition is to become the reference event for academic and industrial researches.

It is expected a strong contribution to the state of the art of this particular subject, as well as an improvement in the reliability of this crucial step in fingerprint-based biometric security systems.