Arif, HossainSikdar, TusharBinte Amin, NafiaShupti, Ayesha AkterFerdous, A.K.M ZubaerDashgupta, Amit2022-09-132022-09-1320222022-01ID: 21301551ID: 18101642ID: 18101196ID: 18101410ID: 17101433http://hdl.handle.net/10361/17212Cataloged from PDF version of thesis.Includes bibliographical references (pages 28-31).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.Artificial Intelligence has brought revolutionary change all around the world prov ing its effectiveness almost in every aspect. AI is not only a science-fiction dream anymore, but also a constant part of our everyday lives. At present, computing is widely used to work smart and precise by eradicating human error and physical labour. An a System that will be recognizing face autonomously is a practical ap plication of AI which made life much easier. After we face the camera, it’ll Capture our photo and send it to the system, to check the database. If the system finds a match, it autonomously check that person’s attendance as present within the table and stores it in the database so that we can view the current version of the atten dance sheet. Throughout the paper we mainly used a Convolutional neural network and pretrained FaceNet model and we got an accuracy of approx. 94.85% using 100 different images. This paper proposes a quick face detection algorithm supported by a classifier, Support Vector Machines (SVM) which we used to separate more non face regions from the taken image. Face is identified by detecting eye and mouth region. The results demonstrate that the accuracy of the detection can be improved further by cutting down false detection.31 Pagesen-USBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Automatic attendance systemFacial recognitionHuman face recognition (Computer science)Artificial intelligenceThesis