Effectiveness Study of Machine Learning Task of Detection Hands Position by Keypoints

This work is about the study of the problem of determining the position of the hands by keypoints. The study is based on using an open dataset with key points on a set of videos with American sign language (ASL) spelling sentences and an approach based on machine learning methods. The main attention is paid to the development of key features that allows to build a high quality and compact machine learning model. In addition, the work investigates the effectiveness of various machine learning models. The results obtained can be useful in the study of labor processes characterized by fast hand movements and short time intervals in algorithms for recognizing technological operations of manual labor on video data.