[32] HAND GESTURE RECOGNITION SYSTEM FOR FINGER COUNTING USING COMPUTER VISION AND MACHINE LEARNING

How to Cite the Article: Setti Sirisha, J. Sujatha, Y. Jyohini, M. Navyasri, K. Tulasi & V. Durga Prasad (2026). Hand Gesture Recognition System for Finger Counting Using Computer Vision and Machine Learning. International Journal of Multidisciplinary Research & Reviews, 5(5),391-398. https://doi.org/10.56815/ijmrr.v5i5.2026.391-398

Abstract

Hand Gesture Recognition (HGR) is an emerging field in Computer Vision that enables natural interaction between humans and machines. This paper presents a real-time finger counting system using Computer Vision and Machine Learning techniques implemented in Python. The proposed system captures live video streams through a webcam and processes the frames to detect hand landmarks. Using MediaPipe hand tracking and OpenCV libraries, the system identifies finger positions and accurately counts the number of raised fingers. The proposed model utilizes landmark-based detection instead of traditional image thresholding methods, thereby improving accuracy under varying lighting conditions. The system can detect multiple hands and compute the total finger count in real time. The application is developed using Streamlit for user interaction and WebRTC for real-time video streaming. The proposed system provides a simple and interactive interface where users can display their fingers in front of the camera and receive instant results. The system has applications in human–computer interaction, virtual classrooms, gaming, robotics control, touchless interfaces, and sign language systems. Experimental results demonstrate that the system is lightweight, efficient, accurate, and deployable on standard computing devices without specialized hardware.