AI based Hand Gestures Recognition System for Educational Purpose
Nikita Mane, Meghsham Jade, Gaurav Thakur, Prof. Nilesh.A. Mohota, Dr. Yogesh.S. Angal
Electronics and Telecommunication Department, Bhivarabai Sawant Institute of Technology & Research
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Today, science and technology develop very quickly making new technologies and ideas easy to apply for the industry to increase productivity and work efficiency. As a result, industrial robots become faster, smarter, and cheaper. More and more companies are beginning to integrate the technology in conjunction with their workforce.[3] It does not mean that robots are replacing humans while it is true that some of the more undesirable jobs are being filled by machines. This trend has several more positive outcomes for the manufacturing industry. The actions of the robot are directed by a combination of programming software and controls. Typically, industrial robots are pre-programmed to perform repetitive tasks. However, there are still jobs that require human interaction. Human robot interaction is aimed at controlling robots that perform jobs that humans cannot work directly. Today, the common control systems are mainly screen and keyboard interaction and it is directly on the robot or remote control. However, it will not be convenient and not user-friendly in some cases. Currently, a new research direction towards the usability of industrial robot control is gesture control. .[3] I.e. robot will observe human gestures through sensors mounting on the body or through an image from the camera to perform corresponding actions that have been set up. The basic advantage of the approach is flexibility and speed for the operator that raises safety requirements for users of heavy robots. Image processing today is no longer complicated achieving high-speed equivalent to real-time or even faster since control methods by image analysis are handy for the user and high efficiency. By creating Deep Neural Network designs where the model will learn to detect the hand motions images throughout an epoch, we are using Deep Learning Computer Vision to recognize the hand gestures. After the model successfully recognizes the motion, user can control the device through hand gestures. The user can choose from a variety of gesture. With this model's improved efficiency, HCI will be easier for the new generation. We shall discuss the use of deep learning for HGRS recognition in this paper.
Key Words HGRS, deep neural network, computer vision, hand
, HCI
