score table

This commit is contained in:
Sefik Ilkin Serengil 2021-12-23 18:10:35 +03:00 committed by GitHub
parent 96b8f9878f
commit 97faf237ae
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -65,7 +65,18 @@ df = DeepFace.find(img_path = "img1.jpg", db_path = "C:/workspace/my_db", model_
<p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/icon/deepface-wrapped-models.png" width="95%" height="95%"></p>
FaceNet, VGG-Face, ArcFace and Dlib [overperforms](https://youtu.be/i_MOwvhbLdI) than OpenFace, DeepFace and DeepID based on experiments. Supportively, FaceNet /w 512d got 99.65%; FaceNet /w 128d got 99.2%; ArcFace got 99.41%; Dlib got 99.38%; VGG-Face got 98.78%; DeepID got 97.05; OpenFace got 93.80% accuracy scores on [LFW data set](https://sefiks.com/2020/08/27/labeled-faces-in-the-wild-for-face-recognition/) whereas human beings could have just 97.53%.
FaceNet, VGG-Face, ArcFace and Dlib are [overperforming](https://youtu.be/i_MOwvhbLdI) ones based on experiments. You can find the scores of those models on both [Labeled Faces in the Wild](https://sefiks.com/2020/08/27/labeled-faces-in-the-wild-for-face-recognition/) and YouTube Faces in the Wild data sets declared by its creators.
| Model | LFW Score | YFW Score |
| --- | --- | --- |
| Facenet512 | 99.65% | - |
| ArcFace | 99.41% | - |
| Dlib | 99.38 % | - |
| Facenet | 99.20% | - |
| VGG-Face | 98.78% | 97.40% |
| Human-beings | 97.53% | - |
| OpenFace | 93.80% | - |
| DeepID | - | 97.05% |
**Similarity**