A Hybrid Campus Security System Combined of Face, Number-Plate, and Voice Recognition

Campus or institution security has been a prominent area of study in recent decades. Facial identification, voice verification, and vehicle license plate recognition have all been used individually in the literature to prevent attackers from entering the facility. Although several academics have agreed that a hybrid recognition system may significantly increase security, hybrid systems are not often discussed in the literature. To overcome this issue, we presented a hybrid driver and vehicle identification module in this study, which can detect both the driver and the vehicle. We applied face recognition and speech verification for driver recognition. Multi-task Cascaded Convolutional Networks were used to crop the faces for facial recognition, while FaceNet was employed for face identification. A three-layer Long Short-Term Memory model was used for voice verification. Finally, Tesseract has been used for car number plate identification. According to the results of the experiments, the suggested approach is capable of detecting both drivers and cars with 0 percent mistake every time, which is a critical improvement for assuring the security of the institutions.