Bank Safeguards System using Machine Learning with Face and Liveness Detection

– Facial Recognition software has a liveness detection feature that prevents hackers from using a customer’s image for impersonation purposes. To Ensuring the security of transactions is currently the biggest threat to banking systems. The use of biometric user authentication has attracted huge sums of money from banks worldwide due to its convenience and acceptability. Especially in an offline environment where ID facial images are compared to digital selfies. In fact, matching selfies to IDs is also used in some broader programs these days, such as automatic immigration checks. The main difficulty of such a process lies in limiting the differences between the comparison face images due to their different origins. Based on deep features extracted by two well referenced Convolutional Neural Networks (CNN). We propose a new architecture for the cross-domain matching problem. The results obtained from the collected data, called Face Bank, show with more than 93% accuracy the power of the proposed head-to-head comparison problem and its incorporation into real banking security systems.