Secure-Data-Masking_one_API-HACK_KPR
- 0 Collaborators
A StreamLit app automates key info extraction from PDFs like resumes, Aadhaar, and PAN cards using OCR for text and scanned docs. GANs generate synthetic data from extracted info for enhanced privacy, streamlining document processing and supporting ML dataset creation. ...learn more
Project status: Under Development
Overview / Usage
This project is a Streamlit app that automatically identifies and extracts key information from PDFs like resumes, Aadhaar, and PAN cards. It handles both text-based and scanned documents using OCR and employs Generative Adversarial Networks (GANs) to create synthetic data based on the extracted information. This tool streamlines document processing, enhances data privacy with synthetic generation, and supports the creation of datasets for machine learning and testing purposes.
Methodology / Approach
This project is a Streamlit app that automatically identifies and extracts key information from PDFs like resumes, Aadhaar, and PAN cards. It handles both text-based and scanned documents using OCR and employs Generative Adversarial Networks (GANs) to create synthetic data based on the extracted information. This tool streamlines document processing, enhances data privacy with synthetic generation, and supports the creation of datasets for machine learning and testing purposes.
Repository
https://ajay212335.github.io/Secure-Data-Masking_one_API-HACK_KPR/