Research/Blog
Face Detection in Artificial Intelligence
- December 13, 2019
- Posted by: CellStrat Editor
- Category: Artificial Intelligence Computer Vision Deep Learning Technology
Face detection is a computer vision problem that involves finding faces in photos. This problem has been solved quite well by classical feature-based techniques, such as the cascade classifier. Recently deep learning methods have achieved state-of-the-art results on standard face detection datasets. One such method is the Multi-task Cascade Convolutional Neural Network, or popularly called MTCNN.
MTCNN helps in simultaneous face detection and landmarks. It is an algorithm consisting of 3 stages, which detects the bounding boxes of faces in an image along with their 5 point face landmarks. It is a very light weight face detector algorithm. Each stage continuously 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.
![](http://www.cellstrat.com/wp-content/uploads/2019/12/MTCNN-Face-detection-1024x307.jpeg)
In stage 1 the input image is scaled down multiple times to build an image pyramid and each scaled version of the image is passed through it’s CNN. In stage 2 and 3 we extract image patches for each bounding box and resize them (24×24 in stage 2 and 48×48 in stage 3) and forward them through the CNN of that stage. Besides bounding boxes and scores, stage 3 additionally computes 5 face landmarks points for each bounding box.