Duplicate detection can be implemented as a simple identification query over database of already registered users. If you do duplicate detection with high threshold (and consequently low FAR), it is best to consider all matches above the threshold. Set candidate count high enough to receive all candidates above the threshold.
How do we best implement duplicate detection? Print
Modified on: Tue, 8 Sep, 2015 at 12:48 PM
Did you find it helpful?Send feedback
Sorry we couldn't be helpful. Help us improve this article with your feedback.