DNN Face detector in OpenCV - OpenCV

A comparison

This model was included in OpenCV from version 3.3. It is based on a Single-Shot-Multibox detector and uses ResNet-10 Architecture as the backbone. The model was trained using images from the web, but the source is not disclosed. OpenCV provides 2 models for this face detector.

• Floating point 16 version of the original caffe implementation ( 5.4 MB )
• 8 bit quantized version using Tensorflow ( 2.7 MB )

The DNN-based detector overcomes all the drawbacks of the Haar cascade based detector without compromising on any benefit provided by Haar. We could not see any major drawback for this method except that it is slower than the Dlib HoG-based Face Detector discussed next.

• YuNet / high-performance-face-detection - a light-weight, fast and accurate face detection model

see also

• OpenCV DNN
  • opencv/samples/dnn/face_detect.py - opencv battery included - ./dnn/example_dnn_face_detect -m=/home/yves/Downloa ds/face_detection_yunet_2022mar.onnx
    • ShiqiYu/libfacedetection - ./detect -m=/home/yves/Downloads/face_detection_yunet_2022mar.onnx
    • models
  • detect_faces.py