Frequently asked questions will be posted as they are submitted.

The registration form has a checkbox for anonymous participation. If we register non-anonymous will we be able to change this status later?

• Anonymous/non-anonymous status may be changed up until the time of submission. After that point, participants must choose to be anonymous or non-anonymous.

Part: Algorithms

1) What should my algorithm output if it cannot process the image?

• Any image that your algorithm cannot process should have an output of -1000 in the results.

2) I would like to not have my algorithm tested against [xyz] dataset, what do I do?

• Please when submitting your executable, if you do not wish your algorithm to process a specific dataset, please let the organizers know. Do not use the -1000 for this scenario.

3) How will not testing my algorithm against a specific dataset affect the overall results?

• The average error scores will not be computed for those who do not participate in all datasets. Therefore, you will not be eligible to be the overall winner. You may, however, be the best submission on a specific dataset.

4) How will a -1000 be handled when computing the error?

• In the table we will separate FerrFake, FerrLive, and Failure to Enroll. In computing the overall average and overall winner, -1000 will be included. In this case a failure to enroll will be considered an error for a live image and correct for a spoof image.

5) Should the algorithm submission be a 32- or 64-bit application?

• We prefer Win32 console applications, but can handle Win64 applications if that is necessary.

Part II: Systems

6) Do you require that a system store an image?

• If the system is able to generate a liveness score for the presented iris or spoof then a stored image is required. If the system cannot sense that a iris or spoof is presented to the device then no image can be stored and then a non-response is recorded.

7) What happens with non-response?

• In the table we will separate FerrFake, FerrLive, Fake Non-Response Rate and Failure to acquire. For a system the ability to not acquire a spoof will be considered correct rejection of a fake and calculated as the Fake Non-Response Rate . The ability to not acquire a live iris will be considered incorrect rejection of a live iris and calculated as the Failure to Acquire rates. In computing the overall average and overall winner, Fake Non-Response rate and Failure to Acquire will be considered.