Hand Gesture Recognizing Model Using Optimized Capsule Neural Network

Hand gestures are a sort of nonverbal communication that may be utilized for many diverse purposes, including deaf-mute interaction, robotic manipulation, human-computer interface (HCI), residential management, and healthcare usage. Moreover, most current research uses the artificial intelligence approach effectively to extract dense features from hand gestures. Since them used neural network models, performance models influences modification hyperparameter enhance recognition accuracy. Therefore, our proposed capsule network, in which internal computations on inputs better encapsulated by transforming findings into tiny vector information outputs. increase accuracy recognizing gestures, has been optimized inserting additional SoftMax layers before output layer CapsNet. Subsequently, tests were assessed then compared. This developed beneficial across all when contrasted against state-of-the-art systems.