Authors:
C. Sathish Kumar, S. Silvia Priscila, G. Abishabackiyavathi, S. Suman Rajest, R. Regin, Chunhua Deming  

Addresses:
Department of Computer Science, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Computer Science, Bharath Institute of Higher Education and Research, Chennai, Tamil Nadu, India. Department of Computer Science, Bishop Heber College (Autonomous), Tiruchirappalli, Tamil Nadu, India. Department of Research and Development (R&D) & International Student Affairs (ISA), Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. Department of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Information Technology Discipline, NUS Graduate School (NUSGS), National University of Singapore, Queenstown, Singapore. sathishc@srmist.edu.in, silviaprisila.cbcs.cs@bharathuniv.ac.in, cs225214102@bhc.edu.in, sumanrajest414@gmail.com, regin12006@yahoo.co.in, chunhuademing@gmail.com 

Abstract:

The identification and detection of hand motions is the focus of this project. Using a web camera, hand gesture photographs are captured. These images are then compared to database images, with the best match returned. In order to create user-friendly interfaces, gesture recognition is one of the most important strategies. For instance, a robot that can identify hand gestures can accept commands from people. Similarly, a robot that can understand sign language would enable people who are deaf or hard of hearing to communicate with it. Recognition of hand gestures may make it possible to use a controller-free application to interact with the system by gestures rather than words. Such an algorithm must be more resilient to consider the plethora of alternative hand locations in three-dimensional space. Using a webcam and computer vision technologies, such as image processing, that can recognize multiple movements for use in computer interface interaction, this research proposes a method for developing a real-time hand gesture recognition system based on “Vision-Based.” Real-time hand gesture recognition has a wide range of practical applications since it can be utilized practically wherever that computer is used. We can open various programs in this project, including word processing and notepad. We used the convolutional neural network approach based on finger curves to invoke apps error-free.

Keywords: Deep Learning; Image Capturing; Foreground Subtraction; Region Extraction; Neural Network Classification; Sign Recognition; Artificial Neural Networks (ANNs); Support Vector Machines (SVMs).

Received on: 29/07/2023, Revised on: 03/10/2023, Accepted on: 23/12/2023, Published on: 01/03/2024

DOI: 10.69888/FTSCS.2024.000193

FMDB Transactions on Sustainable Computing Systems, 2024 Vol. 2 No. 1, Pages: 13-21

• Views : 111
• Downloads : 11

Download PDF