Face Recognition for Examinee Verification
Neetu Anand, Tripti Sharma, Kumar Gaurav · INTERNATIONAL JOURNAL OF NEXT-GENERATION COMPUTING · 2022
In the modern world, facial recognition is playing a vital role in the field of biometric technologies. The reason being simple, it’s a very efficient and developed method compared to the other methods. Its being so precise, errorless and effective gives it an edge over other technologies. There are lot of fields where this fast growing technology is yet to show its effectiveness, one of which is examinations, the identification of the students during examinations. Different kinds of biometric technologies are used in the examination sector in order to identify the students appearing for the exams. Biometric technologies use physical features to identify the person appearing in the exam but many of these traditional methods create room for errors and cheating which can be improved by execution of facial technology.In this research, the approach of Eigenface and fisherface has been used. These techniques are recent and have apparently promising performances, and are representing new trends in this field. Based on previous research that has been done by other researchers about the Eigen face and Fisher face algorithms, where facial image recognition uses Eigenface with different conditions of differentiation from expression, with success rates up to 75%. Ada-boost face recognition, Eigen face PCA and MySQL produce 80% of various different conditions. Face recognition with 93% success with Fisher face by 73 face trials of different expressions and different positions. From previous research, the author wanted to know which algorithm has speed in terms of time, distance and accuracy of photosensitivity in the facial recognition process. By tests of the two algorithms, it produces success percentages and accuracy charts. The Fisherface algorithm is faster than the Eigenface algorithm has an accuracy of 96% and the Fisherface algorithm has an accuracy of 97%.