Hand Sign Recognition System Based on EIT Imaging and Robust CNN Classification

• Published in: IEEE sensors journal Vol. 22; no. 2; pp. 1729 - 1737
• Main Authors: Ben Atitallah, Bilel, Hu, Zheng, Bouchaala, Dhouha, Hussain, Mohammed Abrar, Ismail, Amir, Derbel, Nabil, Kanoun, Olfa
• Format: Journal Article
• Language: English
• Published: New York IEEE 15.01.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Classification; Conductivity; convolutional neural network; Current measurement; EIT; Electrical impedance; Electrical impedance tomography; Electrodes; Forearm; hand sign detection; Image classification; Image reconstruction; Impedance; Muscles; Muscular function; Recognition; regularized Gauss-Newton algorithm; Robustness; sign language; Signs; softmax; support vector machine; Support vector machines; Three dimensional models; virtual hand control; Visualization; Water tanks

Hand sign recognition is gaining importance in human-human and in human-machine communication and interaction. Electrical Impedance Tomography (EIT) is thereby very interesting as it provides information on impedance changes in depth of the Section of the arm, which infers muscle contractions. This...