This article is dedicated to the research of existing methods of analysis and detection of persons in natural conditions. Face recognition based on image analysis is one of the main problems in the implementation of computer vision. The systems of reference measurements allow to define and develop various methods of face detection. Practical experiments were conducted and the algorithms for recognizing faces presented by scientific schools and commercial developments were considered, and also the results of evaluations on all test sets were analyzed based on the data of graphs of truly positive values for assessing the quality and speed of using MALF. Using a detailed assessment, the effectiveness of algorithms in various aspects with respect to several attributes was analyzed. Comparing performance with varying degrees of accuracy, the advantages and disadvantages of algorithms are determined when used in various work scenarios.

Keywords: computer vision, face detection, face detection, face recognition, image analysis algorithms, detection methods, reference measurements