[ozanganeh]

My question is regarding fingerprint evaluation. In the paper that I'm reading, the data set consists of 1,640 fingerprints (from 41 subjects * 10 fingers and each finger contributed 4 impressions; 41 * 10 * 4 = 1,640).

below is a quote from the paper:

“In the first experiment, we compare the matching performance of the proposed hierarchical matcher to that of the individual Level 2 and Level 3 matchers and their score-level fusion [31] across the entire database. For each matcher, the number of genuine and impostor matches are 2,460 (410 * 6) and 83,845 ( (410 * 409) / 2 ), respectively. Note that we exclude symmetric matches of the same pair as well as matches between the same image.”

Image - TinyPic - Free Image Hosting, Photo Sharing & Video Hosting

so based on the ROC curve (in above link) my question is:

1- what are the genuine and impostor matches? Where are the numbers 2,460 and 83,845 are taken from?

2- how they calculated the False Reject and False Accept rates in the plot?

I really appreciate your help.