DEEPFACE.pptx

N A

1. DEEPFACE ALGORITHM

2. DeepFace is a deep learning facial recognition system created by a research group at Facebook. It identifies human faces in digital images. The program employs a nine-layer neural network with over 120 million connection weights and was trained on four million images uploaded by Facebook users

3. In modern face recognition there are 4 steps : Detect Align Represent Classify

4. Given an input image, we first identify the face using six fiducial points. These six fiducial points are 2 eyes, tip of the nose and 3 points on the lips. These feature points are used to detect faces in the image .

5. In this step we generate the 2D-face image cropped from the original image using 6 fiducial points.

6. In the third step, we apply the 67 fiducial point map with their corresponding Delaunay Triangulation on the 2D-aligned cropped image. This step is done in order to align the out of plane rotations. In this step, we also generate a 3D-model using a generic 2D to 3D model generator and plot 67 fiducial points on that manually.

7. Then we try to establish a relation between 2D and 3D using given relation Here to improve this transformation, we need to minimize the loss on \ overrightarrow {P} which can be calculated by the following relation: where, and ∑ is a covariance matrix and dimensions of (67 x 2) x (67 x 2), X3d is (67 x 2) x 8 and [ Tex ]\ overrightarrow {P} [/ Tex ] has dimensions of (2 x 4). We are using Cholesky decomposition to convert that loss function into ordinary least square.

8. The last two layers of the model are fully connected layers. These layers help in establishing a correlation between two distant parts of the face