DocVerify-Automated documents verification system

- Citation Author(s):
-
Tejaswini IngoleSamiksha GunjateSamiksha Bardekar
- Submitted by:
- Tejaswini Ingole
- Last updated:
- DOI:
- 10.21227/yzar-4644
- Data Format:
- Links:
- Categories:
- Keywords:
Abstract
In today’s digital ecosystem, verifying the authenticity of identity documents is essential for secure access control and digital trust. Sectors such as finance, education, government, and employment frequently rely on scanned or digital versions of documents like Aadhaar cards, PAN cards, Voter IDs, Driving Licenses, and Passports. However, this convenience introduces risks related to document forgery and fraudulent activity. The Automated Document Verification System (ADVS) provides a robust, scalable solution to automate identity document verification using Optical Character Recognition (OCR), computer vision, and rule-based pattern recognition, all within a web-based platform built with Flask (Python) and React (JavaScript).
ADVS addresses two core challenges: the inefficiency of manual verification and the absence of centralized, auditable systems for identity validation. It employs Tesseract OCR, enhanced with OpenCV preprocessing, to extract text from user-submitted documents and verifies authenticity using predefined regex-based templates (e.g., Aadhaar’s 12-digit numeric format, PAN’s alphanumeric code). The platform supports three roles—Admin, Verifier, and User—with secure role-based access controls. Admins can manage users, view audit logs, and handle forgery reports, while Users can upload and track verification statuses.
The modular architecture of ADVS supports microservices and scalable deployment. The Flask backend provides RESTful APIs for document handling and user management, while the React frontend ensures an intuitive experience with real-time status updates and document previews. SQLAlchemy with SQLite manages lightweight yet secure data storage, with provisions for scaling to enterprise-grade databases.
A key feature of the system is real-time auditing and forgery detection. Every document interaction is logged with metadata (timestamp, user ID, IP address, etc.), providing transparency and traceability. Evaluation results show over 90% accuracy in validating standard-format documents, with average processing times under three seconds. A user study reported 87% satisfaction, citing ease of use and fast performance.
ADVS enforces session/token authentication, input sanitization, and strict file format controls. Designed for cloud deployment, it can scale horizontally for institutions processing large document volumes. Future enhancements include AI-powered forgery detection, multilingual OCR, real-time government API integration.
Instructions:
As per README file
verification system for documents