Face unlock is a facial recognition technology that enables you to unlock the screen using your face instead of a password or fingerprint.
In this technique, the data is collected as the points on the 2-d plane. You can say in simple words that your face is converted into a 2-d image and then data get collected from that image in the form of digital prints.
By data, here it means features that are extracted and saved in a file for reference while unlock mechanism is initiated. This is a great project to learn about how facial recognition works and how you can implement your own face unlock mechnism on top of existing devices.
The project mainly consists of 3 python files:
Face Generate python script will detect your face and save it in a dataset folder. Then a new folder will be created with your name.
Face Train python file will open the dataset folder and take your image from that and train your face using the K-nearest neighbor algorithm and face_recognition library.
Face Unlock python file will detect your face using the webcam and unlock the system.
As a user, we can automatically lock & unlock our Ubuntu system using computer vision technology. We don't want to manually lock the system. When you move away from your laptop then the system will automatically detect and lock itself to stop any uninvited access.
This project has mainly incorporated K-nearest neighbour algorithm, face recognition library, OpenCV and Tensorflow as the backend for face recognition and face unlock.
All code available here on GitHub.
Fill out this Google Form and get a chance to be featured in this growing AI community
Sign up for our Peer to Peer Computing NetworkGet Early Access
Offer limited to next 10 users only
Q blocks invites you to try out its revolutionary peer to peer GPU computing technology with Free 20 GPU Hours.
Access limited to first 10 individuals only:
Thank you for signing up!
You will receive updates from us on email. Please check your Inbox as well as Spam Folder.
Copyright © Qblocks - Distributed Supercomputer for HPC