Faculty of Engineering /University of Kerbala has discussed the M.A. thesis which is entitled:
(Sign Language Recognition for smart Home Applications)
It is prepared by Atiaf Hikmat Muhammad Ali, supervised by Prof. Dr. Hawra Hassan Abbas and Prof. Dr. Haider Ismail Shehadi.
The researcher presents a system that recognizes sign language of deaf-dumb and converts that sign into a written text and an audible voice by implementing various services such as operating protection systems or controlling smart electrical devices. The proposed system can also be used to control chairs for the disabled, patients’ sleeping beds, moving children’s toys and other applications. This was in real-time to perform the signal with an accuracy of up to 97.5% and recognition time of signal (0.001 seconds) using (Convolution Neural Networks by squeezenet) technique in deep learning approach, which is a subset of machine learning that is based on the principle of neural networks synthetic as a new field of research that deals with finding theories and algorithms that allow the machine to learn by itself by simulating neurons in human body. This approach is the most popular in scientific research today because of the promising results it achieves in various research fields.
