February 2019
Beginner to intermediate
308 pages
7h 42m
English
In Chapter 7, Implementing a Facial Recognition System with Neural Networks, we created a facial recognition system using Siamese neural networks. Siamese neural networks are a special class of neural networks, with a shared, conjoined component. Siamese neural networks accept a pair of images as input, and can be trained to output a distance that is inversely proportional to the similarity of the two images. This forms the idea behind using Siamese neural networks for facial recognition. If the two faces in the input pair of images belong to the same subject, then the distance output should be small, and vice versa. By training a Siamese neural network on positive pairs (faces ...