Veripass- Passport Forgery Detection Using CNN, OCR, and SIFT

The increasing occurrence of passport forgery presents a challenge to national security and the protocols used to verify identities. This research introduces a system for automated passport verification that combines Bilateral Convolutional Neural Networks (CNN) Optical Character Recognition (OCR) and Scale Invariant Feature Transform (SIFT). By examining the limitations of manual passport inspection methods and the growing complexity of forgery techniques this research sheds light on the need for advanced countermeasures. The proposed system revolutionizes the verification process, from document submission to approval resulting in improved efficiency and accuracy. With the use of Bilateral CNN for precise image preprocessing, OCR for text validation, and SIFT for image authentication this system provides a strong defense against passport forgery. This research addresses the requirement for automated forgery detection contributing to the advancement of passport verification systems. It emphasizes how crucial it is to maintain the integrity and security of identity verification processes in response to changing security threats. Index Terms—Passport forgery, Automated verification system, Bilateral Convolutional Neural Networks (CNN), Optical Character Recognition (OCR), Scale Invariant Feature Transform (SIFT)