Convolutional Neural-Network-based Gesture Recognition System for Air Writing for Disabled Person

Air writing is a unique form of natural user interface that involves the recognition of characters and words that are written in the air using the movement of one's hands. This technology has become increasingly prominent and has received considerable attention due to its potential to facilitate more natural and intuitive forms of communication, as well as its applicability to a wide range of fields such as virtual reality, augmented reality, and wearable computing. However, air-writing recognition remains a challenging task due to the complexity and variability of the gestures involved. This research paper proposes an air-writing recognition model that leverages machine learning algorithms to recognize handwritten characters and words in real time. The model is designed to be flexible and adaptable to different types of air-writing gestures and is evaluated using a dataset of air-writing gestures collected from multiple users. The proposed model consists of two main components: a gesture recognition module that pre-processes the input data and extracts relevant features, and a machine learning model that classifies the input gestures based on these features. Experimental results show that the proposed model achieves high levels of accuracy in recognizing air-writing gestures, outperforming existing cutting-edge methods/technologies that are being used. The results demonstrate the potential of the proposed model to be used in a variety of real-world applications, such as text input, and controlling virtual objects in augmented reality.