Skip to content

Latest commit

 

History

History
27 lines (21 loc) · 899 Bytes

README.md

File metadata and controls

27 lines (21 loc) · 899 Bytes
Raw

Face Recognition using Facenet transfer learning

Introduction:

  • Face recognition is a computer vision task of identifying and verifying a person based on a photograph of their face.
  • Face verification is used to verify the given face against a known identity(1:1 mapping).
  • Face recognition is used to verify a given against a database of known faces(1:N mapping).

Concepts:

  • One shot Learning
  • Siamese Network
  • Triple Loss function

Approach:

Programming/Libraries:

  1. Python
  2. Tensorflow
  3. Keras
  4. opencv

References:

  1. FaceNet: A Unified Embedding for Face Recognition and Clustering .
  2. DeepFace: Closing the gap to human-level performance in face verification.
  3. The pretrained model weights
  4. FaceNet github repository