From the course: Deep Learning: Face Recognition
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Finding faces in images with HOG features - Python Tutorial
From the course: Deep Learning: Face Recognition
Finding faces in images with HOG features
- Let's learn how HOG can help us build a face detection model. To train a face detection model, we'll start by collecting lots of images of different faces and converting them the HOG representations like this. These faces will be our training data. Next, we'll use this HOG representation to train the machine learning model. We'll train the model by giving it lots of examples of HOG representations of faces so it can learn what this pattern looks like. Because faces look very obvious in HOG representations, it's pretty easy to train the machine learning algorithm to recognize those patterns. HOG face detectors can perform well with a fairly small amount of training data. Once the model is trained to recognize these kinds of face patterns, we can use it to find faces in other images. Let's detect faces in this image. First, we'll convert this image into a HOG representation. Next, we'll use our HOG face detection model as a sliding window detector. We'll slide our face detector over…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.