CSC Senior Students win the 1st position for project (Lip-reading) and 4th position for (BREACTOR) in “Three Minute Thesis” Competition in AUC Tech Summit. The winners were chosen based on a panel and public voting. The panel included professors from AUC and representatives from companies around Egypt.
Lip-reading is to understand what someone is saying by watching the movements of their mouth. Lipreading plays a vital role in human communication and speech understanding. However, it is a difficult task for humans. Thus, the main goal of this project is to develop a deep learning approach for the real-time detection of spoken words. The training of a deep-layered CNN and RNN is being used to convert lips movement to written words.
BREACTOR is designed to help drivers who can be drowsy while driving for different reasons like exhaustion for example. It can detect drowsiness of a driver through Biological Signals and send alerts to wake him up. BREACTOR uses emotiv epoc device to read Brain signals. The emotiv must be ready to work and start reading signals and filtering all all of them to extract the specific feature domains then classify the features by using some algorithm for classification . Finally the signal will be saved and checked. If the signal result is “drowsy”, the system will alert the driver and repeat the whole process every one minute. On the other hand, if the signal is “normal” the process will be repeated every 5 minutes.
