Hidden Faces Detection for Enhancing Security at ATMs
K. P. Aswanth · International Journal for Research in Applied Science and Engineering Technology · 2020
Automatic Teller Machine (ATM) plays a vital role in our modern economic society. Around 1,30,000 ATM centers are functioning across India. A real-time intelligent video analytics offers advanced monitoring capabilities that gives sophisticated video surveillance to recognize abnormal activities. A person covering his/her face with a scarf, mask or helmet in ATM center is one of the abnormal activity. In such scenario, an automatic face detection algorithm is required to, warn and alert when the person is trying to cover his/her face in ATM. The detection of face is obtained using Deep Learning Convolutional Neural Network (DCCN) architecture such as YOLOv3 that performs very well in the fast detector category when speed is important. The output of the DCCN is then reported to the ATM to take appropriates steps and prevent attacker from completing the transaction.