$ sudo apt-get install libhdf5-dev libc-ares-dev libeigen3-dev # install the dependencies (if not already onboard) # remove old versions, if not placed in a virtual environment (let pip search for them) First, we need to install the MTCNN library on the device. We’ll test our application on a Raspberry Pi 3B device, 1GB RA<, with the Raspbian 32-bit OS. Can we use this AI model on a resource-constrained edge device? In this article, we’ll test our facial detection application on a Raspberry Pi and share ideas on running it in real time mode. Having completed the previous article, we now have a good working DNN model for face detection, which can be run together with the face alignment algorithm on a PC to find faces in video streams. You are welcome to download this project code. We assume that you are familiar with DNN, Python, Keras, and TensorFlow. Create a simple face database and fill it with faces extracted from images or videos.
Run the face detection DNN on a Raspberry Pi device, explore its performance, and consider possible ways to run it faster, as well as to detect faces in real time.Consider face alignment and implement some alignment algorithms using face landmarks.Discuss the existing AI face detection methods and develop a program to run a pretrained DNN model.In the first (current) half of this article series, we will: The two main base stages of face recognition are person verification and identification. The best face recognition systems can recognize people in images and video with the same precision humans can – or even better. Face recognition is one area of Artificial Intelligence (AI) where deep learning (DL) has had great success over the past decade.