A Neural Network based Attendance Monitoring and Database Management System using Fingerprint Recognition and Matching

Most authentication systems use fingerprints for identification. The uniqueness of fingerprint for each individual forms the basis of faultless identification. However, the image generated by the scanner may give varying results during each scan which thereby results in a major drawback in most existing systems. Thus, this paper involves the implementation of robust portable Neural Network based system to provide an efficient matching algorithm for fingerprint authentication systems. Image processing algorithms and appropriate choice of features for the training of neural networks is presented. The system is implemented on Raspberry Pi with appropriate interfacing modules to make the system standalone. As the proposed system is portable, it can be used as an attendance monitoring system in classrooms. The back-end system involves the processes of image acquisition and processing to create a suitable database. The corresponding hardware model is created in MATLAB and then deployed in the Raspberry Pi-3 module to form a standalone system.