Detecting faces using Haar cascades

- [Instructor] The technique I used…in OpenCV to detect faces in an image is…called a Haar Cascade.…The details about how it works are beyond the…scope of this course, but if you're interested…in learning more about Haar Cascades,…there's a nice, short article on the OpenCV website.…At a very high level, the Haar feature-based classifier…analyzes sections on an image in search…of patterns or features that indicate…whether or not that part of the image contains a face.…

For facial detection, there are over 6,000 features…that the algorithm needs to evaluate…to determine if a section of an image contains a face.…And that ends up being a lot of processing.…Especially considering that most parts…of an image are usually not a face.…So to speed things up, rather than evaluating…all 6,000 features before making a decision,…the algorithm uses a cascade to evaluate a…few features at a time to determine…whether or not the image section it's evaluating…could possibly be a face.…

If the first feature it analyzes could be a face,…