This research study proposes automated student attendance management system (AAMS) with the help of image processing and deep Learning methods. The AAMS system used to manage, create, and maintain the student IN and OUT timing class wise with the help of face detection and recognition methods. The face recognition is problematic due to the dimension, clearness, orientation, appearance, illumination, and intensity of facial pictures. The AAMS system is designed to recognize figures representing the faces of positive pictures and eliminated the backdrop of negative images with environment by using dataset. The main aim of this system is to improve responsiveness and alertness of AAMS system procedure, and reduce the burden of manual workload, for instance, adding, updating, and manipulating the records of attendance individual as well as automatic calculations, the number of absentees and presenters created on class and cordiality of class then compile report in format CSV and spreadsheet documents. The AAMS uses the images and videos for recording the attendance of the students by identifying variant facial features. This System managing the attendance more accurate and effective. The suggested AAMS approach provides outstanding accuracy with the help of Feature engineering and Deep Learning methods.