Evolution of the Viola–Jones object detection method: a survey

The Viola and Jones algorithm is one of the most well-known methods of object detection in digital images. Over the past 20 years since the first publication, the method has been extensively studied, and many modifications of the original algorithm and its individual parts have been proposed by researchers and engineers. Some ideas popularized by Paul Viola and Michael Jones became the basis for many other algorithms of object localization in images. This paper presents a description of Viola and Jones algorithm, the history of its development and modifications in the context of various problems of object localization in images, as well as a description of the current state of affairs: the method's place in the era of convolutional neural networks extensive application.