It is based on Single-Shot-Multibox detector and uses ResNet-10 Architecture as backbone. This model was included in OpenCV from version 3.3. The major drawback of this method is that it gives a lot of False predictions.Each member of the list is again a list with 4 elements indicating the (x, y) coordinates of the top-left corner and the width and height of the detected face. the output is a list containing the detected faces. The above code snippet loads the haar cascade model file and applies it to a grayscale image. FaceCascadePath = './haarcascade_frontalface_default.xml' įtectMultiScale(frameGray, faces) įor ( size_t i = 0 i < faces.size() i++ )