TY - JOUR AU - Tjut Zuraiyah AU - Sufiatul Maryana AU - Asep Kohar PY - 2022/11/30 Y2 - 2024/03/29 TI - Automatic Door Access Model Based on Face Recognition using Convolutional Neural Network JF - MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer JA - matrik VL - 22 IS - 1 SE - Articles DO - https://doi.org/10.30812/matrik.v22i1.2350 UR - https://journal.universitasbumigora.ac.id/index.php/matrik/article/view/2350 AB - Automatic door access technology by utilizing biometrics such as fingerprints, retinas and facial structures is constantly evolving. The use of masks during the Covid-19 Pandemic and post-pandemic has become an obligation wherever humans are active. The study aimed to create an automated door access model using Convolutional Neural Network (CNN) algorithms and Amazon Rekognition as cloud-based software. The CNN algorithm is applied to classify faces wearing masks or not wearing masks. The CNN architecture model uses sequential, convolution2D, max polling 2D, flatten dan dense. The hardware includes the Raspberry Pi, USB Webcam, Relay, and Magnetic Doorlock. The test results were obtained from the results of the accuracy plot on the Convolutional Neural Network model with an accuracy rate of 99% at an epoch value of 8 with a learning time of 67 seconds. ER -