IndexAbstractIntroductionConclusionAbstractThe Suspicious Activity Detection System aims to provide a reliable system for online exams based on rigorous online security and true candidate authentication. The main aim of the project is to detect the human being who cheats in the exam. The human face and human behavioral pattern play an important role in person identification. The proposed system aims to identify abnormal head movements, thus identifying the copy. It will also identify a student who leaves his/her exam location or exchanges location with another student or looks into another student's computer. Say no to plagiarism. Get a tailor-made essay on "Why Violent Video Games Shouldn't Be Banned"? Get an Original Essay Introduction Online exams have become very popular in today's IT world. It has replaced all the inconveniences of offline exam. But even today there is a big question regarding the security of online exams. Student authentication during online exam is a big issue. The main disadvantage of online exams is that the candidate can easily use any unauthorized method. The system consists of the developed software running on the computer on which the online exam is to be conducted. The webcam is connected to the same computer. The designed software runs in the background along with the online exam at the forefront. For the online exam, the computers used are placed at an adequate distance from each other so that, in normal situations, only one student (the intended one) is in front of the webcam. In the proposed system, the student should be equipped with a webcam equipped with a computer system and should be positioned so that his face can be clearly visible from the front view. As an initial check, the student will be asked to show the entire room where the online exam will take place. The first part of the check is face detection. After detecting the face, the video and audio input is also captured to detect if any unwanted people are present, especially if there is someone talking inside the room. There is a possibility that the student user will try to copy from a file on the computer. Then all these are given as inputs to the heuristics-based inference system. By analyzing all these inputs the inference system decides whether there is any negligence or not. The literature survey provided us with various documents and techniques that will be useful for the development of the project. These papers used various image processing techniques for face detection and tracking which can be explained as follows: Heuristics-based Automatic Online Surveillance System[1] 2015 15th IEEE International Conference on Advanced Learning TechnologiesThis paper proposes a new multimodal method for online supervision using a combination of image processing, audio processing and PC monitoring techniques. In the proposed system the remote supervisor only needs to inspect the examination room. The proposed heuristic-based online automatic proctoring system combines image processing, audio processing and PC monitoring techniques which eliminates the need to have a remote proctor during the exam to monitor cheating. Automated Video Surveillance to Detect Suspicious Human Activities[2]International Journal of Emerging Technologies in Computational and Applied Sciences (IJETCAS) The proposed system aims to identify abnormal head movements, thus prohibiting copying. It will also identify a student who leaves his seat or exchanges his position with another student or looks into the.