Face Verification And Recognition Using Siamese Network
- 0 Collaborators
Face recognition is of two types face verification and face recognition. This project implements both the ideas. Here I used a pre-trained model which has been trained on triplet loss function. ...learn more
Project status: Published/In Market
Overview / Usage
This project can be used to verify the identity of the person(Face Verification) as well as tell who the person is(Face Recognition).
Methodology / Approach
A Siamese Network that is used to calculate a 128 vector encoding which consists of two identical neural networks, each taking one of the two input images. The output 128 vector of the two images are compared and if they are close enough its a match. The model has been trained using triplet loss function in which their are 3 images namely anchor, positive example and negative example.
Technologies Used
Python
Tensorflow
Keras
Ipython
Repository
https://bitbucket.org/tanuj1121999/face_verification_and_recognition