<html><body><div><div><span>Hey everyone,</span></div><br><div><span>I've been playing with the face recognition in DigiKam for a few months now trying to sort through about 500,000 photos, and I've run into a few problems.</span></div><br><div><span>I'm making a few assumptions here, so please let me know if I'm way off-base.</span></div><br><div><span>I started out by tagging a few hundred photos of various family members (let's just say Person 'A', 'B', 'C', etc...).</span></div><div><span>After I did that, I ran the recognition at 90% and it managed to get a few images that were nearly duplicates of the ones I tagged. I confirmed them.</span></div><br><div><span>Then I dropped it down to 80% and a bunch were detected incorrectly.</span></div><br><div><span>While going through several thousand images...at one point I accidentally tagged 20 or 30 images of Person A as Person B.</span></div><br><div><span>I noticed there's no "Undo", and that's understandable based on my knowledge of how training databases work.</span></div><div><span>Anyways, I went in to Person B, found the images of Person A and corrected them to be Person A.</span></div><br><div><span>But from that point on, I appear to be doomed.</span></div><br><div><span>The system still frequently detects Person A as Person B, and I've made the mistake a few more times while classifying images.</span></div><br><div><span>Yesterday I went through every single face tag and corrected probably 200 images in total that were confirmed incorrectly.</span></div><br><div><span>Anyways, I re-ran the recognition tool, and it's </span><i><span>still</span></i><span> guessing people incorrectly...</span></div><br><div><span>My guess is the training database "learned" my mistakes and correcting them doesn't really undo the damage I initially did.</span></div><br><div><span>Is there a way to "reset" the facial recognition database and re-train it from scratch by saying "The images I have already tagged as Person A, Person B, etc... are correct"?</span></div><br><div><span>Is that what "Clear and rebuild all training data" does in Maintenance? I'm hesitant to try that option as it will probably take a solid day or two to run and I don't want to lose all the manual tagging I've done.</span></div><br><div><span>Thanks!</span></div><br><div><span>-A</span></div></div></body></html>