In real case scenarios, there is often a need for detection and recognition of faces not just in images, but in videos. For example, this is a necessary prerequisite for security cameras, filters on social networks, identification at work and many other cases where cameras are used. The pictures are static, but videos can be seen as a series of pictures, or frames. All video clips are constructed of a constant number of frames in a second, usually between 25 and 60, to many other variations are possible.

In our previous post related to Face detection, an overall procedure has been shown how faces are detected in images. The difference here, is that we need to process every video frame (image) through the Neural Network so that we can detect a face or faces in it. OpenCV contains useful functions for opening and reading video files.

In conclusion, this is the first important step in any system that uses face detection in videos, where we do not have only images with human faces present. In addition to that, in the next post we will learn about Yolo Object Detection.

More resources on the topic:

• Building a Face Detection Model on a Video using python
• CNN Object Localization
• CNN Landmark Detection
• Building a Face Detection Model on an Image using Python