2018-09-10 06:16:57 -0600 | received badge | ● Famous Question (source) |
2017-11-29 04:25:54 -0600 | received badge | ● Notable Question (source) |
2017-08-09 00:50:57 -0600 | received badge | ● Popular Question (source) |
2016-09-06 08:07:41 -0600 | received badge | ● Enthusiast |
2016-08-30 09:58:20 -0600 | commented question | Improving face recognition accuracy @berak I've been using a minimum of 20 images per person, and I choose such a huge resolution for the raw images so that I had a lot of detail to start with. I forgot to mention that I was trying different sizes for preprocessing. I tried 500x500, 1000x1000, then of course 1500x1500 (basically not resizing) and that's when I noticed the trend in confidence values. |
2016-08-29 17:50:01 -0600 | asked a question | Improving face recognition accuracy I'm working on a Face Recognition program using My issue: The confidence values between Person A (myself) and Person B (a friend) are a bit too close. There is a "fair" amount of difference, but not enough to set a threshold without getting false positives/negatives. I wrote a script to recognize Person A over a set of images for Person B and calculate the average confidence so I could see how much they differ by, and I noticed that as the face size in Step 3 of Preprocessing (see below) increased, the difference decreased.
My expectation was that by increasing the face size, there would be more detail and thus the difference would increase. Detected face sizes in this case were roughly My question: How can I improve face recognition accuracy? Below is some information about my project. Thanks. Files used:
Image information:
Preprocessing Steps:
Training Steps:
Recognition Steps:
|