Face Recognition Based Smart Attendance System

Abstract

Education institutes today are concerned about the consistency of students ' performance. One cause of this decrease in student performance is the inadequate attendance. There are several ways to mark your attendance, the most common ways to sign or call the students. It took longer and was problematic. From now on, a computer-based student attendance checking system is required that supports the faculty to keep records of attendance. We have used an intelligent attendance system based on face recognition in this project. We have proposed to implement a Smart Attendance System for Face Recognition through this large applications are incorporated. The present implementation includes facial identification that is time saving and eradicates the possibilities of proxy attendance due to the facial authorization. This system can now be used in an area in which participation plays an important role. Raspberry Pi, Open CV and Dlib using python are the basic requirements for this system. The system implemented uses LBPH face recognizer to identify the face of the person in real time. Eigen faces and Fisher faces are affected both by light and we cannot ensure perfect light conditions in real life. An improvement in the LBPH faces recognizer to overcome this problem. This system compares the image of the test and the training image and determines who is and is not present. The attendance data is stored in an excel sheet that is automatically updated in the system. If a student is absent a message will be automatically sent to their parent’s phone number using GSM. Student’s can check their attendance using an Android application that we have developed using MIT app Inventor.