In order to blur faces shown in images, you need to first detect these faces and their position in the image. Luckily for us, I already wrote a tutorial on face detection, we'll only be using its source code, feel free to check it out for further detail on how the face detection code works. To get started, installed required dependencies:
The particular threshold values are tuned for face detection and in this case, the pruning speeds up the processing. minSize: Minimum window size. By default, it is set to the size of samples the classifier has been trained on (~20x20 for face detection). How to Train the Prototype?
Returns Inference Engine internal backend API. See values of CV_DNN_BACKEND_INFERENCE_ENGINE_* macros.. Default value is controlled through OPENCV_DNN_BACKEND_INFERENCE_ENGINE_TYPE runtime parameter (environment variable).
Mar 14, 2018 · Face liveness detection: A mechanism based on an analysis of how ‘alive’ a test face is. This is usually done by checking eye movement, such as blinking and face motion.