Juan Tapia & Daniel Benalcazar

Deep learning solutions to detect such frauds have been presented in the literature oriented to information security and forensics. However, due to privacy concerns and the sensitive nature of personal identity documents, developing a dataset with the necessary number of examples for training deep neural networks is challenging. This talk explores different methods for synthetically generating ID card images to increase the amount of data while training fraud-detection networks. These methods include image processing analysis approach, Generative Adversarial Networks and new application based on Foundation models.