8000 GitHub - misaaldsouza/face-recognition: To recognize and manipulate faces using python/command line with the face_recognition library built using dlib software. The model has an accuracy of 99.38%.
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

To recognize and manipulate faces using python/command line with the face_recognition library built using dlib software. The model has an accuracy of 99.38%.

Notifications You must be signed in to change notification settings

misaaldsouza/face-recognition

Repository files navigation

Face Recognition

It is one of the many wonders that AI research has brought forward to the world. A technology capable of verifying a person from a digital image or a video frame from a video source. Generally, it works by comparing selected facial attributes from given image with faces within a database (img/unknown).

Installation


Python provides a simple face_recognition command line tool that allows us to do face recognition on a folder of images. Before installing the library we need dlib library pre-installed.

The following command will install the tool.

pip3 install face_recognition

The library works in three simple steps :

• Identify a face in a given image
• Identify specific features in the face
• Compare it with the unknown images 
• If found , it generates a face encoding vector of 128 values

-- based on this encoding, we can measure the similarity between two face images that can tell us if they belong to the same person.

Screenshots


findfaces.py
Capture

pullfaces.py

capt

Applications


• Access Control

• Criminal Identification

• Healthcare

• Smarter Advertising

About

To recognize and manipulate faces using python/command line with the face_recognition library built using dlib software. The model has an accuracy of 99.38%.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

0