In this tutorial, you will learn how to optimize the fingerprint minutiae quality threshold. The Detection Error Trade-off (DET) curve before and after using a better threshold is shown below.
As can be observed, there is a marked improvement by simplying using only minutiae of sufficiently high quality.
1. Back up the original features directory.
2. Create a new copy of the features directory which contains fingerprint templates with only sufficiently high quality minutiae.
Let’s take a look at an xyt file using head features_original/100_1.xyt in bash, which gives the following output:
The first column shows the row and column of minutiae and the third column shows the orientation. The last column is what we are interested in; it shows the quality of the minuatiae. The code below will filter out the minutiae with low quality by using a threshold of 20 and then writing the feature files back to the features directory.
3. Generate the score matrix
4. Analyse the scores
First, we load the scores produced in the previous tutorial; and call it scores.
Next, we get the genuine and impostor scores, reusing the variable user created in the previous tutorial.