Given still or video images of a scene, face recognition is a technique to identify or verify one or more persons in the scene using a stored database of faces.
"Face Recognition" generally involves two stages:
- Face Detection, where a photo is searched to find any face (shown here as a green rectangle), then image processing cleans up the facial image for easier recognition.
- Face Recognition, where that detected and processed face is compared to a database of known faces, to decide who that person is (shown here as red text)
There are two directly related websites to provide actively updated information:
- The Face Recognition Homepage to provide relevant information in the area of face recognition;
- The Face Detection Homepage to to gather all useful information about finding faces;
OpenCV (Open Source Computer Vision) is a library of programming functions for real time computer vision. It includes very good implementation for face detection and face recognition.
- Face Detection using OpenCV; Implemented in facedetect.c;
- Face Recognition using OpenCV with Eigenfaces or Principal Component Analysis method (PCA);
The following tutorials show how to use OpenCV for face detection and recognition:
- "Introduction to Face Detection and Face Recognition" by Shervin Emami;
- "OpenCV haartraining (Rapid Object Detection With A Cascade of Boosted Classifiers Based on Haar-like Features)" by Naotoshi Seo;