Article · Trudy Universiteta · March 30, 2024

Development of a System for Recognizing Human Images and Speech by a Robot in the Python Software Environment

Dauren Baltabay, Zhadyra T. Zhumasheva

Abstract

Recently, the technology of information and search systems for facial recognition for the purpose of identifying a person has become widespread. Personal identification subsystems using image and speech recognition technology can be used in automated securitysystems for the purpose of identifying wanted persons with the simultaneous transmission of relevant operational information to identity identification services. The purpose of this work is to develop a system for recognizing the robot image and speech of a person in the Python software environment. Moreover, the word «recognition» has two meanings. The first is the word-by-word conversion of spoken speech into the corresponding written text, as well as the selection of the person's face, eyes and converting it to a shade of gray. The second is the correct reaction to a statement containing a request or a reference from the speaker and the drawing of rectangular shapes on the contour of the face and eyes. By combining speech recognition with speech synthesis, you can build a system of communication between a person and a machine. The motive for intensive research on speech and image recognition in the fields of industry, science, and defense arose in connection with the rapid development of the information industry, covering computers, office automation, communications, defense and robotics.

Speech and dialogue systemsFace recognition and analysisRobotics and Automated Systemsface recognitionspeech recognitionpersonal identification

Development of a System for Recognizing Human Images and Speech by a Robot in the Python Software Environment

Abstract

More by Dauren Baltabay