Comprehensive Framework for Real-Time Hand Gesture Recognition on Mobile Platforms using Machine Learning,TensorFlow Lite, Keras, MediaPipe, OpenCV and NumPy

Roshani Rajesh khobragade; Rutul Ganthade; Palak Janbandhu; Aastha Nitnaware; Dr. Archana Potnurwar; Amol Bamrotwar

Comprehensive Framework for Real-Time Hand Gesture Recognition on Mobile Platforms using Machine Learning,TensorFlow Lite, Keras, MediaPipe, OpenCV and NumPy

January 2026

Vol-12, Issue-1

Paper ID: 27926

ISSN: 2395-4396

Downloads: 0

Abstract & Details

Research Area

Information Technology / Computer Engineering / Machine Learning

Keywords

Numpy Hand gesture hand recognition Machine learning Hand gesture recognition mobile vision MediaPipe TensorFlow Lite Keras OpenCV NumPy real-time HCI.

Abstract

Hand gesture recognition (HGR) has emerged as a natural and intuitive interaction paradigm for human–computer interaction (HCI), particularly in mobile and embedded systems where traditional input mechanisms are constrained. This manuscript presents a detailed and end-to-end framework for real-time hand gesture recognition designed specifically for on-device mobile deployment. The proposed system integrates MediaPipe Hands for efficient landmark extraction, OpenCV and NumPy for vision preprocessing and feature computation, Keras with TensorFlow for deep learning model development, and TensorFlow Lite (TFLite) for optimized on-device inference on Android platforms. A custom dataset was collected from 20 participants under multiple lighting and background conditions, covering both static and dynamic gesture classes. Experimental results demonstrate high recognition accuracy for static gestures (96.8%) and robust performance for dynamic gestures (91.4%), with an average end-to-end latency of approximately 20 ms, enabling real-time execution at around 50 frames per second. Detailed evaluation of accuracy, latency, and resource utilization confirms the feasibility of deploying gesture recognition systems on commodity smartphones. The manuscript also discusses limitations, practical deployment challenges, and future research directions, including multi-hand recognition, adaptive learning, and multimodal interaction.

License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Author Information

#	Name	Institute / Affiliation
1	Roshani Rajesh khobragade	Priyadarshini College of Engineering, Hingna, Nagpur
2	Rutul Ganthade	Priyadarshini College of Engineering, Hingna, Nagpur
3	Palak Janbandhu	Priyadarshini College of Engineering, Hingna, Nagpur
4	Aastha Nitnaware	Priyadarshini College of Engineering, Hingna, Nagpur
5	Dr. Archana Potnurwar	Priyadarshini College of Engineering, Hingna, Nagpur
6	Amol Bamrotwar	Priyadarshini College of Engineering, Hingna, Nagpur

How to Cite

Use the following formats to cite this article in your research.

APA Style

khobragade, Roshani Rajesh, Ganthade, Rutul, Janbandhu, Palak, Nitnaware, Aastha, Potnurwar, Dr. Archana, & Bamrotwar, Amol (2026). Comprehensive Framework for Real-Time Hand Gesture Recognition on Mobile Platforms using Machine Learning,TensorFlow Lite, Keras, MediaPipe, OpenCV and NumPy. International Journal of Advance Research and Innovative Ideas In Education, 12(1), 98-105.

MLA Style

khobragade, Roshani Rajesh, et al. "Comprehensive Framework for Real-Time Hand Gesture Recognition on Mobile Platforms using Machine Learning,TensorFlow Lite, Keras, MediaPipe, OpenCV and NumPy." International Journal of Advance Research and Innovative Ideas In Education, vol. 12, no. 1, 2026, pp. 98-105.

IEEE Style

Roshani Rajesh khobragade, Rutul Ganthade, Palak Janbandhu, Aastha Nitnaware, Dr. Archana Potnurwar, and Amol Bamrotwar, "Comprehensive Framework for Real-Time Hand Gesture Recognition on Mobile Platforms using Machine Learning,TensorFlow Lite, Keras, MediaPipe, OpenCV and NumPy," International Journal of Advance Research and Innovative Ideas In Education, vol. 12, no. 1, pp. 98-105, 2026.

Vancouver Style

khobragade Roshani Rajesh, Ganthade Rutul, Janbandhu Palak, Nitnaware Aastha, Potnurwar Dr. Archana, Bamrotwar Amol. Comprehensive Framework for Real-Time Hand Gesture Recognition on Mobile Platforms using Machine Learning,TensorFlow Lite, Keras, MediaPipe, OpenCV and NumPy. International Journal of Advance Research and Innovative Ideas In Education. 2026;12(1):98-105.

Harvard Style

khobragade, Roshani Rajesh, Ganthade, Rutul, Janbandhu, Palak, Nitnaware, Aastha, Potnurwar, Dr. Archana, & Bamrotwar, Amol (2026) 'Comprehensive Framework for Real-Time Hand Gesture Recognition on Mobile Platforms using Machine Learning,TensorFlow Lite, Keras, MediaPipe, OpenCV and NumPy', International Journal of Advance Research and Innovative Ideas In Education, 12(1), pp. 98-105.

Chicago Style

khobragade, Roshani Rajesh, et al. "Comprehensive Framework for Real-Time Hand Gesture Recognition on Mobile Platforms using Machine Learning,TensorFlow Lite, Keras, MediaPipe, OpenCV and NumPy." International Journal of Advance Research and Innovative Ideas In Education 12, no. 1 (2026): 98-105.

Turabian Style

khobragade, Roshani Rajesh, et al. "Comprehensive Framework for Real-Time Hand Gesture Recognition on Mobile Platforms using Machine Learning,TensorFlow Lite, Keras, MediaPipe, OpenCV and NumPy." International Journal of Advance Research and Innovative Ideas In Education 12, no. 1 (2026): 98-105.