Face recognition problem

Face recognition problems commonly fall into two categories:

• Face Verification - “is this the claimed person?”. For example, at some airports, you can pass through customs by letting a system scan your passport and then verifying that you (the person carrying the passport) are the correct person. A mobile phone that unlocks using your face is also using face verification. This is a 1:1 matching problem.
• Face Recognition - “who is this person?”. For example, the video lecture showed a face recognition video of Baidu employees entering the office without needing to otherwise identify themselves. This is a 1:K matching problem.

FaceNet learns a neural network that encodes a face image into a vector of 128 numbers. By comparing two such vectors, you can then determine if two pictures are of the same person.

you will:

• Implement the triplet loss function
• Use a pertained model to map face images into 128-dimensional encodings
• Use these encodings to perform face verification and face recognition

1 - Encoding face images into a 128-dimensional vector

The key things you need to know are:

• This network uses 96x96 dimensional RGB images as its input. Specifically, inputs a face image (or batch of m face images) as a tensor of shape (m, nc, nh, hw) = (m, 3, 96, 96)
• It outputs a matrix of shape (m, 128) that encodes each input face image into a 128-dimensional vector

So, an encoding is a good one if:

• The encodings of two images of the same person are quite similar to each other
• The encodings of two images of different persons are very different

FRmodel = faceRecoModel(input_shape=(3, 96, 96))
FRmodel.compile(optimizer='adam', loss=triplet_loss, metrics=['accuracy'])

1.2 - The Triplet Loss

For an image x, we denote its encoding f(x), where f is the function computed by the neural network.

Training will use triplets of images (A, P, N):

• A is an "Anchor image–a picture of a person.
• P is a “” image–a picture of the same person as the Anchor image.
• N is a “Negative” image–a picure of a different person than the Anchor image.

What you should remember:

• Face verification solves an easier 1:1 matching problem; face recognition addresses a harder 1:K matching problem.
• The triplet loss is an effective loss function for training a neural network to learn an encoding of a face image.
• The same encoding can be used for verification and recognition. Measuring distances between two images’ encodings allows you to determine whether they are pictures of the same person.