Face Recognition Using Convolutional Neural Networks
V.K.N Kamlesh Pai, Manoi Balrai, Sachinkumar Mogaveera, Deepak Aeloor · 2018 2nd International Conference on Trends in Electronics and Informatics (ICOEI) · 2018
Face recognition is a common biometric authentication technique used to analyse the face images and extract useful recognition information from them, which are always called as a feature vector that is used to distinguish the biological features. Face Recognition process begins with extracting the coordinates of features such as width of mouth, width of eyes, pupil, and compare it with a stored face template. The aim of the proposed system is to design an autonomous security system that performs face recognition based surveillance combined with a hardware mechanism to lockup the secured region. Haarcascade algorithm is used to detect and extract the face from an image thereby storing samples in order to train the system. The system consists of a buzzer alarm and two cameras diagonally placed. The camera locates, tracks people entering the secured room, recognize the individual and message is passed to the control room which is stored in the log file. Any unauthorized access is logged along with a buzzer alarm to notify the control room followed by locking the exit points of the system. This system focuses on system security using face recognition which can be installed at banking suits.