A Novel Hybrid Deep Learning Architecture for Dynamic Hand Gesture Recognition

• Published in: IEEE access Vol. 12; pp. 28761 - 28774
• Main Authors: Hax, David Richard Tom, Penava, Pascal, Krodel, Samira, Razova, Liliya, Buettner, Ricardo
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Artificial neural networks; Classification; CNN; Computational modeling; Computer architecture; convolution neural networks; Convolutional neural networks; Deep learning; dynamic hand gesture; Dynamics; Feature extraction; Feature maps; Gesture recognition; hand gesture recognition; Human computer interaction; hybrid architecture; inception model; inception-v3 architecture; Long short term memory; LSTM; Machine learning; Neural networks; recurrent neural network; Recurrent neural networks; RNN; video hand gesture; Videos

Hand gestures are a form of natural communication used in human-computer interaction, however, when gestures are video-based, extraction of features for classification is complex. Current machine learning models struggle to achieve high accuracies when using videos recorded in realistic environments...