// Service
Tarek Abou Rjeily builds real-time computer-vision systems for clients in Lebanon and the Gulf — software that sees what people can't, then detects, matches, and alerts the instant it happens. Examples include a live exam-proctoring system (YOLOv8 + face recognition) for Arab Open University and a privacy-first, face-recognition photo-delivery platform for events.
Real-time exam integrity for Arab Open University. YOLOv8 + face recognition flag phones, head-turns, and unknown faces; alerts include the flagged frame in Telegram.
Read case study →Face-recognition photo delivery for events. One selfie returns matching event photos — built on a self-hosted face engine, privacy-first.
Read case study →Tarek Abou Rjeily builds real-time exam proctoring, face recognition and matching, behaviour and object detection, and visual quality checks, using YOLOv8, OpenCV, MediaPipe, and self-hosted face engines like CompreFace.
Privacy is designed in: for example, BSoura stores mathematical face descriptors rather than photos, isolates each event behind unguessable links, and auto-deletes data — so the system can match faces without becoming a surveillance liability.
Message me on WhatsApp, email tarekabourjeily@outlook.com, or see all services.