From the course: OpenCV for Python Developers
Join today to access over 24,400 courses taught by industry experts.
Challenge: Eye detection
From the course: OpenCV for Python Developers
Challenge: Eye detection
(upbeat music) - [Instructor] Let's complete this chapter of the challenge. Specifically, let's try and find all the eyes in an image and place circles around them. To do this, leverage a Haar Cascade method similar to how we detected faces in the previous module. This time use the provided haarcascade_eye.xml file which has specifically been pre-trained for detecting eyes in an image. Additionally, try to reduce the number of false positives and false negatives as much as possible. In this scenario, a false positive is drawing a circle where there is not an eye and a false negative is not drawing a circle where there is an eye. Compared to the overall face detection sample before expect to change what the cascade model inputs need such as the minimum size to better match the size of the eyes to be detected. Additionally, be mindful that the model outputs bounding boxes, but you need to draw circles instead. This exercise…
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.
