Detect Faces in images and live webcam feed
MTCNN (Multi-task Cascaded Convolutional Neural Networks) is an algorithm consisting of 3 stages, which detects the bounding boxes of faces in an image along with their 5 Point Face Landmarks. Each stage gradually improves the detection results by passing it’s inputs through a CNN, which returns candidate bounding boxes with their scores, followed by non max suppression.
This is an implementation of MTCNN. MTCNN gives 5 keypoints in a face, using those 5 keypoints, this code generates 4 more keypoints. It can detect multiple faces in an image or in live webcam feed.
- opencv _ _ _ _ _ _ 4.1
- tensorflow _ _ _ _ 1.14
- numpy _ _ _ _ _ _ 1.16
- os
- mtcnn