Gesture Recognition using Convolutional Neural Network
G Shanmuga Priya, V Nitisha Sree, K Magisha, S Pooviga · 2023
Hand gesture detection, which is adaptable and user-friendly, is one of the most active study areas in the field of human-computer interfaces. Using the gesture recognition system, a system is designed that can be deployed to communicate with disabled people or to administer a product. Excellent internal consistency commonalities in hand gesture postures, slight variances, non-uniform surroundings, with user-specific hand form and shape variations all offer considerable obstacles to creating an efficient hand gesture detection mechanism. In this article a hand gesture detection method which is user independent is examined using custom characteristics such convolutional neural networks (CNN). A technology known as Gesture Recognition uses mathematical algorithms to interpret human gestures. The dataset is collected and stored in the form of files and folders. Using CNN algorithm, the collected dataset is compared with the threshold value of the given input and thus the result is presented in the form of text or voice. Gesture Recognition System is an inventive user interface that eliminates the challenges associated with using remote controls for home appliances by replacing the remote-control system with hand gestures. Deep learning and computer vision are two tools that can be used to further the cause. Using the suggested method, an authentic implementation of gesture - based system is constructed and evaluated.