Year: 2025
Type: article
Abstract: The "Real-Time Hand Gesture Recognition System" aims to enhance human-computer interaction using computer vision and machine learning techniques. Using the webcam for real-time video capture, the system uses OpenCV to process each frame in real-time. Thus, it recognizes hand gestures using models such as Cvzone's, Hand Detector or Mediapipe. After the hand is detected, it crops, resizes, and normalizes it for further review. Then, a pre-trained Convolutional Neural Network (CNN) model is used to classify the gesture, mapping that into predefined labels such as numbers, letters, or ASL signs. This therefore provides an efficient and natural interface for the users in particular with assistive technology applications.
Authors: Jerald Siby, Hilwa Kader, Jinsha Jose
Language: English
Subfield: Human-Computer Interaction
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W1658995172