From 97faf237ae6e45bad921919df041912581d6addb Mon Sep 17 00:00:00 2001 From: Sefik Ilkin Serengil Date: Thu, 23 Dec 2021 18:10:35 +0300 Subject: [PATCH] score table --- README.md | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 88054d8..4211239 100644 --- a/README.md +++ b/README.md @@ -65,7 +65,18 @@ df = DeepFace.find(img_path = "img1.jpg", db_path = "C:/workspace/my_db", model_

-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**