Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{176053,
        author = {AKULA ASHOK and SURI JAYAPRADA and EMANDI SHANMUKH and SHAIK KHASIM and DANDU RAMA SAI PRANEETHA and KANITHI TARUN KUMAR},
        title = {Real-Time Hand Gestures Recognition System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {4948-4951},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176053},
        abstract = {Within the realm of computer science, hand gestures are most common form of communication, and real-time recognition can improve human-system interaction easily, especially for the individuals with speaking disabilities. This research focuses on introducing a real-time hand gesture recognition system, that works on a Convolutional Neural Network (CNN) which is trained on keypoints which are collected using Mediapipe, optimizing the efficiency and accuracy. A custom dataset is used with 30000 samples. The system is deployed as a React-based web application, where recognized gestures are translated into structured sentences with audio output, improving the accessibility and smooth communication. This React based web application is deployed in Cloud platform AWS for easy access. The resulted system works well in detected my custom hand gestures. The experimental results demonstrate high classification accuracy and real-time responsiveness, highlighting the system’s potential for assistive applications and interaction user experiences. It has a long scope for further development.},
        keywords = {Hand Gesture Recognition, Mediapipe, Convolutional Neural Network (CNN), Real-time interaction, AWS.},
        month = {April},
        }