deepface

Deepface is a lightweight facial analysis framework including face recognition and demography (age, gender, emotion and race) for Python. Modern face recognition pipelines consist of 4 stages: detect, align, represent and verify. Deepface handles all these common stages in the background. You can use the framework with a just few lines of codes

Face Recognition

Verify function under the DeepFace interface is used for face recognition.

from deepface import DeepFace
result = DeepFace.verify("img1.jpg", "img2.jpg")

print("Is verified: ", result["verified"])

{
   "verified": true,
   "distance": 0.25638097524642944,
   "max_threshold_to_verify": 0.40,
   "model": "VGG-Face",
   "similarity_metric": "cosine"
}

Each call of verification function builds a face recognition model from scratch and this is a costly operation. If you are going to verify multiple faces sequentially, then you should pass an array of faces to verification function to speed the operation up. In this way, complex face recognition models will be built once.

dataset = [
	['dataset/img1.jpg', 'dataset/img2.jpg'],
	['dataset/img1.jpg', 'dataset/img3.jpg']
]
result = DeepFace.verify(dataset)

Face recognition models

Face recognition can be handled by different models. Currently, VGG-Face , Google Facenet, OpenFace and Facebook DeepFace models are supported in deepface. The default configuration verifies faces with VGG-Face model. You can set the base model while verification as illustared below. Accuracy and speed show difference based on the performing model.

vggface_result = DeepFace.verify("img1.jpg", "img2.jpg") #default is VGG-Face
#vggface_result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "VGG-Face") #identical to the line above
facenet_result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "Facenet")
openface_result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "OpenFace")
deepface_result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "DeepFace")

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

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, Euclidean Distance and L2 form. The default configuration finds the cosine similarity. You can alternatively set the similarity metric while verification as demostratred below.

result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "VGG-Face", distance_metric = "cosine")
result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "VGG-Face", distance_metric = "euclidean")
result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = "VGG-Face", distance_metric = "euclidean_l2")

Facial Attribute Analysis

Deepface also offers facial attribute analysis including age, gender, emotion and race predictions. Analysis function under the DeepFace interface is used to find demography of a face.

from deepface import DeepFace
demography = DeepFace.analyze("img4.jpg") #passing nothing as 2nd argument will find everything
#demography = DeepFace.analyze("img4.jpg", ['age', 'gender', 'race', 'emotion']) #identical to the line above
#demographies = DeepFace.analyze(["img1.jpg", "img2.jpg", "img3.jpg"]) #analyzing multiple faces same time

print("Age: ", demography["age"])
print("Gender: ", demography["gender"])
print("Emotion: ", demography["dominant_emotion"])
print("Emotion: ", demography["dominant_race"])

Analysis function returns a json object.

{
"age": 32.49221594557578,
"gender": "Woman",
"race": {
   "asian": 3.928472101688385, 
   "white": 55.44567108154297, 
   "middle eastern": 15.896821022033691, 
   "indian": 3.050043433904648, 
   "latino hispanic": 20.90577930212021, 
   "black": 0.7732132915407419
},
"dominant_race": "white",
"emotion": {
   "angry": 3.1055836006999016, 
   "fear": 1.1844050139188766, 
   "neutral": 86.2661361694336, 
   "sad": 7.137920707464218, 
   "disgust": 0.0001227657776325941, 
   "happy": 2.245445176959038, 
   "surprise": 0.06038688006810844
}, 
"dominant_emotion": "neutral"
}

Installation

The easiest way to install deepface is to download it from PyPI.

pip install deepface

Alternatively, you can directly download the source code from this repository. GitHub repo might be newer than the PyPI version.

git clone https://github.com/serengil/deepface.git
cd deepface
pip install -e .

Initial tests are run for Python 3.5.5 on Windows 10 but this is an OS-independent framework. Even though pip handles to install dependent libraries, the framework basically needs the dependencies defined in the requirements. You might need the specified library requirements if you install the source code from scratch.

Playlist

Deepface is mentioned in this youtube playlist.

Disclaimer

Reference face recognition models have different type of licenses. This framework is just a wrapper for those models. That's why, licence types are inherited as well. You should check the licenses for the face recognition models before use.

Herein, OpenFace is licensed under Apache License 2.0. FB DeepFace and Facenet is licensed under MIT License. The both Apache License 2.0 and MIT license types allow you to use for commercial purpose.

On the other hand, VGG-Face is licensed under Creative Commons Attribution License. That's why, it is restricted to adopt VGG-Face for commercial use.

Support

There are many ways to support a project - starring⭐️ the GitHub repos is just one.

You can also support this project through Patreon.

Licence

Deepface is licensed under the MIT License - see LICENSE for more details.

Logo is created by Adrien Coquet. Licensed under Creative Commons: By Attribution 3.0 License.

extreme-assistant / deepface