Using Multi Adaptive Neuro Fuzzy Inference Systems to Identify Fraud Bank Checks

Abstract

This research is to use multiple Adaptive Neuro Fuzzy Inference Systems (ANFIS) to design and build an image processing algorithm to quickly and easily detect a fraud or altered bank check in real time. With the help of MATLAB Fuzzy Logic and Image Processing Toolboxes, this algorithm can be used to quickly detect most fraud or altered bank checks via an ATM scanner when a fraud or altered check is deposited to an ATM. The testing and validation processes have been performed to confirm the effectiveness and correctness of this detecting algorithm. The current correct detecting rate is about 80% for checks deposited via ATMs.