Abstract - This paper examines the main methods and principles of image formation, display of the sign language recognition algorithm using computer vision to improve communication between people with hearing and speech impairments. This algorithm allows to effectively recognize gestures and display information in the form of labels. A system that includes the main modules for implementing this algorithm has been designed. The modules include the implementation of perception, transformation and image processing, the creation of a neural network using artificial intelligence tools to train a model for predicting input gesture labels. The aim of this work is to create a full-fledged program for implementing a real-time gesture recognition algorithm using computer vision and machine learning.