Detecting skimming devices in ATM through image processing

Card skimming is the act of using a skimmer to illegally collect data from the magnetic stripe of bank card of ATM card. The information copied onto another blank card's magnetic stripe, is then used by the thief to withdraw cash in the name of the actual account holder. Skimming works by replacing a card reader like an ATM with a camouflaged counterfeit card reader. The counterfeit reader records all the data on a credit, debit or ATM card as it passes through the skimmer. In this paper, we propose a technique to detect the skimming devices when attached to the ATM machine through image processing. A semi-automated system utilizing MATLAB to analyze and process the acquired images is presented. The proposed solution exploits a systematic set of actions to detect the skimming devices when attached to the ATM machine by utilizing existing surveillance camera technology to read the images and find out if any additional items have been attached to the machine. The algorithm can however be enhanced in a way to be integrated with other external systems to translate the outcome so as to reduce the risk of card skimming/cloning crimes.