Scribd
Upload
301 views9 pages

Deepface

DeepFace is a facial recognition system developed by Facebook that uses a deep learning algorithm. It identifies faces in images with 97% accuracy, similar to humans. The DeepFace algorithm uses a 4-step pipeline: it detects faces, aligns them, represents the facial features using a deep neural network, and classifies the images by comparing feature vectors. DeepFace was trained on 4 million Facebook images and achieves state-of-the-art accuracy on standard datasets.

Uploaded by

Fahad Raza
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
301 views9 pages

Deepface

DeepFace is a facial recognition system developed by Facebook that uses a deep learning algorithm. It identifies faces in images with 97% accuracy, similar to humans. The DeepFace algorithm uses a 4-step pipeline: it detects faces, aligns them, represents the facial features using a deep neural network, and classifies the images by comparing feature vectors. DeepFace was trained on 4 million Facebook images and achieves state-of-the-art accuracy on standard datasets.

Uploaded by

Fahad Raza
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

DeepFace

and deep learning for face recognition


Facebook DeepFace

DeepFace is a facial recognition system:

● It identifies human faces in digital images


● Trained with 4M facebook images
● The system is 97% accurate (human level accuracy)
● Developed by Facebook AI Research
Face Recognition Pipeline

DeepFace algorithm is a pipeline composed of 4 stages:

1. Detect the face in the image

2. Align the detected face

3. Represent facial images through a large deep neural network

4. Classify the image comparing a feature vector (classifier)


Step1 - Face Detection

Face Detection identifies human faces in


digital image.

● The detected face is cropped and


used as input for the alignment
step.
● DeepFace algorithm uses already
developed Face Detection
algorithm.
Step 2 - Face Alignment - 2D Alignment

2D Alignment
1. Detect 6 “fiducial points” to scale,
rotate and translate the image.
2. The fiducial points are detected
using SVR (Support Vector
Regressor).
Step 2 - Face Alignment - 3D Alignment

3D Alignment
1. Detect 67 “fiducial points” (using
SVR).
2. Compare them with a fixed 3D model
of a generic face.
3. Reconstruct the 3D model of the
detected face.
4. Generate the 3D-aligned version of
the crop.
5. The final image is given to the DNN.
Step 3 - Representation

● C1, M2, C3 → Convolutional networks: extract low level features


● L4, L5, L6 → Locally connected networks: extract high level features
● F7, F8 → Fully connected networks: capture correlation between features discovered in distant parts of
the face image
Step 4 - Classification

● Cosine Angle

DeepFace
descriptor
vector

● Weighted distance

DeepFace
descriptor
● Siamese Network
vector
Conclusions

Experiments results:

● YTF Dataset
○ YoutubeFace Database collects
3,425 YouTube videos of 1,595
subjects.
○ 91.4% accuracy

● LFW Dataset
○ Labeled Faces in the Wild
consists of 13,323 web photos of
5,749 celebrities.
○ 97.35% accuracy

You might also like