Join us and get access to thousands of tutorials and a community of expert Pythonistas.

Unlock This Lesson

This lesson is for members only. Join us and get access to thousands of tutorials and a community of expert Pythonistas.

Unlock This Lesson

Hint: You can adjust the default video playback speed in your account settings.
Hint: You can set your subtitle preferences in your account settings.
Sorry! Looks like there’s an issue with video playback 🙁 This might be due to a temporary outage or because of a configuration issue with your browser. Please refer to our video player troubleshooting guide for assistance.

Viola-Jones Object Detection Framework

Austin Cepalia
Traditional Face Detection With Python Austin Cepalia 01:19
Recommended Tutorial Ask a Question

The Viola-Jones algorithm is named after two computer vision researchers who proposed the method in 2001: Paul Viola and Michael Jones.

They developed a general object detection framework that was able to provide competitive object detection rates in real time. It can be used to solve a variety of detection problems, but the main motivation comes from face detection.

The Viola-Jones algorithm has 4 main steps, and you’ll learn more about each of them in the sections that follow:

  1. Selecting Haar-like features
  2. Creating an integral image
  3. Running AdaBoost training
  4. Creating classifier cascades

Given an image, the algorithm looks at many smaller subregions and tries to find a face by looking for specific features in each subregion. It needs to check many different positions and scales because an image can contain many faces of various sizes. Viola and Jones used Haar-like features to detect faces.

00:00 We are using what is called the Viola-Jones object detection framework.

00:06 This framework was developed by two computer vision researchers in the early 2000s, Paul Viola and Michael Jones. Their goal was to create an algorithm that could provide competitive object detection rates in real time.

00:22 It can be used to solve a variety of detection problems, but their main motivation behind the algorithm was face detection—how convenient. The algorithm is broken up into four parts.

00:34 You’ll learn about each one in depth in the following videos. The algorithm selects Haar-like features; it creates an integral image; it runs AdaBoost training; and finally, it creates classifier cascades, which can be used to detect the presence of faces within images.

00:53 Given a specific image, the algorithm looks at many smaller subregions and tries to find a face by looking for specific features in each subregion. It needs to check many different positions and scales because an image can contain many faces of various different sizes.

01:11 Viola and Jones used what are called Haar-like features to start this process.

Become a Member to join the conversation.