github/deepface
1
1
Fork 0
mirror of https://github.com/serengil/deepface.git synced 2025-06-07 12:05:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

face recognition models comparision

Browse Source
This commit is contained in:
Sefik Ilkin Serengil 2020-02-10 17:15:11 +03:00 committed by GitHub
parent efd0933cec
commit 48e5dee67f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -24,6 +24,8 @@ facenet_result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "Facenet")
openface_result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "OpenFace") openface_result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "OpenFace")
``` ```
VGG-Face has the highest accuracy score but it is not convenient for real time studies because of its complex structure. Facenet is a complex model as well. On the other hand, OpenFace has a close accuracy score but it performs the fastest. That's why, OpenFace is much more convenient for real time studies.
## Similarity ## Similarity
These models actually find the vector embeddings of faces. Decision of verification is based on the distance between vectors. Distance could be found by different metrics such as [`Cosine Similarity`](https://sefiks.com/2018/08/13/cosine-similarity-in-machine-learning/), Euclidean Distance and L2 form. The default configuration finds the **cosine similarity**. You can alternatively set the similarity metric while verification as demostratred below. These models actually find the vector embeddings of faces. Decision of verification is based on the distance between vectors. Distance could be found by different metrics such as [`Cosine Similarity`](https://sefiks.com/2018/08/13/cosine-similarity-in-machine-learning/), Euclidean Distance and L2 form. The default configuration finds the **cosine similarity**. You can alternatively set the similarity metric while verification as demostratred below.
@ -34,8 +36,6 @@ result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "VGG-Face", distan
result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "VGG-Face", distance_metric = "euclidean_l2") result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "VGG-Face", distance_metric = "euclidean_l2")
``` ```
VGG-Face has the highest accuracy score but it is not convenient for real time studies because of its complex structure. Facenet is a complex model as well. On the other hand, OpenFace has a close accuracy score but it performs the fastest. That's why, OpenFace is much more convenient for real time studies.
## Verification ## Verification
Verification function returns a tuple including boolean verification result, distance between two faces and max threshold to identify. Verification function returns a tuple including boolean verification result, distance between two faces and max threshold to identify.