Classical Algorithm vs. Machine Learning in Objects Recognition

This article focuses on two most popular methods of detecting regular shapes in the pictures. Over the past years, image processing and object recognition are entering our lives more and more. The difference between a classical algorithm and machine learning was analyzed, in case of a tennis ball recognition on photos. It has been created on own dataset to avoid a uniform background and bright colors. Images were taken with a low-cost camera in different conditions. Creating the classical algorithm and machine learning and comparing the accuracy, false flags and performance of the two methods are described.