Traditional attendance systems require manual intervention, consume valuable class time, and are prone to errors such as proxy attendance and inaccurate record keeping. To overcome these limitations, this project presents a Face Recognition and Attendance System that automates the attendance process using computer vision and facial recognition techniques. The proposed system is developed using Python, OpenCV, Tkinter, and MySQL, while the Local Binary Pattern Histogram (LBPH) algorithm is employed for face recognition. The system begins with secure administrator authentication, followed by student registration where academic and personal information is stored in the database. A facial dataset is then generated by capturing multiple images of each registered student through a webcam. These images are used to train the recognition model, producing a classifier that identifies students during real-time operation. Whenever a student's face is successfully recognized, the corresponding attendance is automatically recorded with the student's ID, name, department, date, time, and attendance status. Unknown faces are rejected to improve system security and reliability. Experimental evaluation demonstrates that the proposed system provides fast recognition, minimizes manual effort, prevents proxy attendance, and maintains accurate attendance records. The developed application is suitable for educational institutions and can also be extended for attendance management in offices and organizations. Index Terms — Face Recognition, Smart Attendance System, OpenCV, Python, LBPH Algorithm, MySQL, Haar Cascade, Computer Vision.