Face Recognition in Real Time for Attendance Marking System
Shubhankar Sharma, Tanushree Gupta, R. G. Suresh Kumar · Zenodo (CERN European Organization for Nuclear Research) · 2018
The face recognition system is developed to be operated in real time, scanning, comparing and giving the desired output with minimal time delays. This paper describes an Error Correcting Output Codes (ECOC) based model which has been used in our software. ECOC is an output representation method capable of discovering some of the errors produced in classification tasks. ECOC classifier is used for training and improving the generally use feed forward neural networks (FFNN), in order to enhance the precision of the classification systems. The experimental results on the database made from the pictures of students of Bhagwan Parshuram Institute of Technology show the correctness and authenticity of our model. With a minimal delay and error rate high reliability is achieved. The paper is concluded with future uses of this model and concept.