Using OpenCV with MediaPipe and Tensorflow to classify gestures and actions

In the previous sections of the chapter you have familiarized with the idea of Artificial Neural Networks, and how they can be used in a computer vision context, coupled with OpenCV.

This wonderful match of Computer Vision and ML/AI, coupled with the exponential increase in computing power, enabled engineers to resolve really difficult challenges, such as general object detection and recognition, tracking etc.

Like every other area of software engineering, at first some tasks are difficult to accomplish, then they become run of the mill, then a plethora of libraries and frameworks becomes available in many programming languages, often hiding the underlying logic.

In many respects, it’s like driving a car: you don’t have to know how an engine works to drive a car, and if all you want to do is to drive the car from point A to point B respecting limits and rules of the road, then knowing how an engine...