RN SHETTY TRUST®
RNS INSTITUTE OF TECHNOLOGY
Autonomous Institute Affiliated to VTU, Recognized by GOK, Approved by AICTE, New Delhi
(NAAC ‘A+ Grade’ Accredited, NBA Accredited (UG - CSE, ECE, ISE, EIE and EEE)
Channasandra, Dr. Vishnuvardhan Road, Bengaluru - 560 098
Ph:(080)28611880,28611881 URL: [Link]
INTERDISCIPLINARY PROJECT WORK
AI-BASED DOCUMENT
VERIFICATION SYSTEM
Phase I Presentation
28th April 2026
Team Members: {Names, USN, Class &
Section) Name of the Supervisor: Dr. Manohar P
• Mallinath K 1RN25CY058 CSE-CY A
• Hemaraj J 1RN25CY044 CSE-CY A Review Team Members:
• Manoj K 1RN25CY061 CSE-CY A
• Prajwal Gowda A M 1RN25CI117 CSE-AIML
• Amit 1RN25CV004 CV A
• Raghavendra 1RN25CV038 CV A
Date 06/04/2026 CSE-CY
Agenda
01 Introduction
Agenda 02 Problem Definition & Objectives
03 Literature Survey
04 Possible List of Solutions & Block diagram
05 Methodology/Prototype development plan
06 Hardware /Software requirement
07 Deliverables & Applications
08 Estimate of Expenditure
09 Timeline for completion of project
Date 06/04/2026
Introduction
The AI-based Document Verification System is an interdisciplinary
project that uses artificial intelligence to automate document
validation. It applies technologies like OCR and image processing
to detect forged or tampered documents quickly and accurately,
reducing manual effort and improving security.
Date 06/04/2026 CSE-CY 3
Key Points:
• Automates document verification using AI
• Uses OCR for text extraction
• Detects forgery with image processing
• Saves time and reduces errors
• Useful in banking, education, and government sectors
Date 06/04/2026 Dept. of Computer Science and Engineering (Cyber Security) 4
Problem Definition & Objectives
Problem Definition
• Manual document verification is slow, error-prone, and vulnerable to fraud.
With the increasing number of digital documents, it becomes difficult to
accurately detect forged or tampered documents using traditional methods.
Objectives
• Develop an AI-based system for automatic document verification
• Detect forged or tampered documents accurately
• Reduce manual effort and human errors
• Improve speed and efficiency of verification
• Ensure secure and reliable validation process
Date 06/04/2026 CSE-CY 5
Literature Survey
Title Authors Publication Year Methodology
Optical Character
Google Research /
Recognition for Introduced Tesseract OCR for text extraction;
R. Smith Tesseract OCR 2007
Document widely used but limited to OCR only.
Project
Digitization
Image-Based
Forgery Detection S. Bayram et Used edge detection and pixel analysis; limited for
IEEE Conference 2009
Using Digital al. complex forgeries.
Image Processing
Date 06/04/2026 CSE-CY 6
Literature Survey
Title Authors Publication Year Methodology
Automated KYC
P. Sharma et International Journal Combined OCR + AI for identity verification in
Verification System 2021
al. (IJRASET) banking.
using OCR and AI
AI-Based
Document Integrated OCR, NLP, and ML for end-to-end
M. Patel et al. Elsevier Journal 2023
Verification using verification.
OCR and NLP
Date 06/04/2026 CSE-CY 7
Possible List of Solutions
• AI-based document verification using machine learning models
• OCR-based text extraction and validation
• Image processing to detect tampering (blur, edits, mismatches)
• QR code / barcode verification for authenticity
• Database cross-checking with official records
• Blockchain-based document storage for enhanced security
Date 06/04/2026 CSE-CY 8
Block diagram
Date 06/04/2026 Dept. of Computer Science and Engineering (Cyber Security) 9
Methodology/Prototype development plan
• Collect dataset of genuine and forged documents
• Preprocess data (image cleaning, resizing, enhancement)
• Apply OCR to extract text from documents
• Perform feature extraction (text + visual features)
• Train AI/ML model for classification (valid vs fake)
• Integrate database/API for cross-verification
• Develop user interface for document upload
• Test and evaluate system accuracy
• Deploy prototype for real-time verification
Date 06/04/2026 CSE-CY 10
Hardware /Software requirement
Hardware
• Computer/Laptop (Minimum 8GB RAM, i5 or equivalent)
• GPU (optional, for faster model training)
• Scanner or Camera for document input
• Stable Internet connection
Software
• Programming Language: Python
• Libraries: OpenCV, TensorFlow/PyTorch, NumPy, Pandas
• OCR Tool: Tesseract OCR
• Frameworks: Flask / Django (for web app)
• Database: MySQL / MongoDB
• IDE: VS Code / PyCharm
Date 06/04/2026 CSE-CY 11
Final Deliverables & Applications
Deliverables
• Working AI-based document verification system
• Trained ML model for fraud detection
• User interface for document upload & results
• Integrated OCR and database verification module
• Project report and documentation
• Demo/Presentation of the system
Applications
• Banking & financial institutions (KYC verification)
• Educational institutions (certificate validation)
• Government services (ID verification)
• Recruitment systems (document screening)
• E-commerce & fintech platforms (user verification)
Date 06/04/2026 CSE-CY 12
Estimate of Expenditure
• Software Tools: NIL
• Hardware: NIL (existing system used)
• Cloud Services: ₹1,000 – ₹3,000
• Internet & Miscellaneous: ₹500 – ₹1,000
• Documentation & Printing: ₹500 – ₹1,000
Total Estimated Cost: ₹2,000 – ₹5,000
Date 06/04/2026 CSE-CY 13
Timeline for completion of project
TIMELINE PHASE ACTIVITY
Week 1 Requirement analysis, dataset collection
Planning
Week 2 Design Data preprocessing, OCR implementation
Week 3 Development Feature extraction, model building
Week 4 Integration UI development, database & model integration
Week 5 Testing & Deployment Testing, evaluation, final deployment
Date 06/04/2026 CSE-CY 14
References
• R. Smith, “An Overview of the Tesseract OCR Engine,” Proc.
International Conference on Document Analysis and Recognition
(ICDAR), vol. 2, pp. 629–633, 2007.
• G. Bradski, “The OpenCV Library,” Dr. Dobb’s Journal of Software
Tools, vol. 25, no. 11, pp. 120–125, 2000.
• M. Abadi et al., “TensorFlow: A System for Large-Scale Machine
Learning,” Proc. 12th USENIX Symposium on Operating Systems
Design and Implementation (OSDI), pp. 265–283, 2016.
• S. Agarwal, A. Gupta, and N. Jain, “Document Forgery Detection
Using Machine Learning,” International Journal of Computer
Applications, vol. 182, no. 10, pp. 15–20, 2018.
Date 06/04/2026 CSE-CY 15
Date: 02/04/2026 CSE-CY 16