Year: 2025
Type: article
Abstract: The detection and secure storage of personally identifiable information (PII) in government-issued documents, such as PAN cards, is a crucial aspect of digital security. This project presents a deep learning-based approach using Convolutional Neural Networks (CNN) and YOLOv8 for the detection of real and fake PAN cards. The system allows users to upload a PAN card image, which is then analyzed for authenticity. If the card is real, the detected PII is annotated using YOLOv8. To ensure privacy, the system incorporates base64 encryption for redaction and utilizes blockchain for secure storage. Users can later retrieve and decrypt the image using a transaction hash, ensuring secure access to stored information. The integration of deep learning and blockchain provides a robust and reliable solution for PII protection in government documents
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4409478391