From the course: Code Clinic: C++
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Detect faces using Haar Cascades - C++ Tutorial
From the course: Code Clinic: C++
Detect faces using Haar Cascades
- [Instructor] OpenCV comes with a few different classifiers for different image analysis tasks, and the one recommended for face detection is the HaarCascade. This method was introduced by Paul Viola and Michael Jones. And the low-level details are beyond the scope of this course. But if you're interested in learning more, there are various references that you can go check out, including the OpenCV website. At a high level, the Haar Cascade is a machine learning approach where the Cascade is trained to using a lot of positive and negative images. That is, images that the program should recognize as a face, and images that the program should recognize as not a face. For each image used for training, a set of features are used to evaluate to what degree each image contains these features. Examples of features are shown here and are applied to small regions of an image. An example of a feature specific for face recognition…
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.