Home/Problem Statements/SIH26188

SIH26188SoftwareBlockchain & Cybersecurity

₹1,50,000 Prize (₹75k Joint)

•

Deadline: 20 September 2026

•

Submitted Ideas: 0/500

Al-Based Fake Identity & Document Screening System

Ministry / Organization: Ministry of Home Affairs

Department: Sashastra Seema Bal (SSB), Police II Division

SIH Official Portal

Technical Complexity

8/10

Dataset Accessibility

7/10

36h Hackathon Viability

9/10

Step 0 • Zero-Jargon Layman Summary

“Border guards currently check passports and visas manually, which is slow and misses sophisticated fakes. We need to build an AI system that instantly scans identity documents, detects hidden tampering, checks the person's face, and flags high-risk travelers in seconds.”

The DecodeX PS Decoder™

Deconstructed Problem Blueprint

Step 1

WHAT TO BUILD?

An AI-powered document screening and identity verification platform comprising OCR extraction, validation rule engines, tampering detection, and face matching modules, wrapped in an operational dashboard for border security personnel.

Step 2

WHO IS IT FOR?

The problem is faced by Sashastra Seema Bar (SSB) and Ministry of Home Affairs border personnel dealing with massive passenger throughput. The users are border security officers, checkpoint inspectors, and backend intelligence analysts.

Step 3

WHY DOES IT EXIST?

Manual verification is prone to human fatigue, error, and blindness to microscopic digital forgeries or photo-swapping. High passenger volumes force security compromises, leading to illegal infiltration and security threats.

Step 4

INPUT → PROCESS → OUTPUT ARCHITECTURE PIPELINE

01 • Inputs & Telemetry

High-resolution scanned images or live capture of passports, visas, national IDs, driving licenses, and live facial feed from checkpoint cameras.

02 • Processing & AI Core

Document type classification, deep OCR text extraction, EXIF metadata analysis, Error Level Analysis (ELA) and CNN-based tampering/forgery detection, rule-based database matching, and Cosine similarity face embedding matching.

03 • Actionable Deliverables

Real-time risk score dashboard, green/yellow/red clearance flags, detailed tamper heatmaps highlighting altered text/photos, and a structured audit trail report for security agencies.

Step 5

CONSTRAINTS

Must operate in low-bandwidth or offline environments at remote border outposts.
Sub-second or low-latency processing speed (< 3 seconds per document) to prevent passenger queues.
High accuracy requirement to minimize false positives that could delay genuine citizens.
Strict data privacy compliance regarding identity document storage and processing.

Step 6

JURY METRICS

OCR Extraction Accuracy (Character Error Rate < 1%)
Tampering Detection Precision and Recall (> 95%)
End-to-End Processing Latency (< 3 seconds on standard edge hardware)
UI/UX Simplicity and clarity of risk scores for non-technical security guards

Step 7

CORE BOTTLENECK

Building a robust tampering detection engine that can simultaneously identify physical alterations (peeled lamination, cut-and-paste photos) and digital forgeries (font mismatch, pixel manipulation, metadata mismatch) without relying on restricted proprietary government databases.

Why You Should Choose This PS (Pros)

Extremely high national security impact aligning directly with Ministry of Home Affairs priorities.
Clear modular structure (OCR, Validation, Tampering, Face) makes task delegation straightforward during a 36-hour hackathon.
Strong 'wow-factor' potential via live webcam document scanning and visual heatmaps showing forged areas.

Challenges & Risks to Watch (Cons)

Availability of authentic vs. forged training datasets for document tampering is scarce.
Handling various international passport formats and diverse lighting conditions at borders is challenging.
Crowded domain if teams rely purely on basic OCR wrappers without true AI forgery detection.

Hackathon Blueprint

Recommended Tech Stack & Grand Finale Features

Frontend & Mobile

React.jsTailwind CSSLucide Icons

Backend & APIs

FastAPI / PythonOpenCVPillow

AI / ML & Models

PaddleOCR or Tesseract for text extractionInsightFace / FaceNet for face verificationCustom PyTorch CNN / Error Level Analysis (ELA) for tampering detection

Database & Cloud

PostgreSQLSQLite (for local offline caching)Local filesystem / MinIO

Killer Features to Impress the SIH Jury

AI Forgery Heatmap: Visual overlay highlighting exact pixels where digital or physical tampering (photo swap, font edit) occurred.

Offline-First Edge Sync: Fully functional local processing node that syncs audit logs with central servers once network connectivity is restored.

Instant Cross-Check Matrix: Automatic matching of passport MRZ (Machine Readable Zone) data against extracted visual OCR fields to catch discrepancy frauds.

Auditable Risk Scoring Engine: Transparent breakdown showing why a passenger was assigned a red/yellow/green flag.

View Official SIH 2026 Portal Raw Text

▼

•Background Common challenges faced at border checkpoints:

•Fake passports and visas

•Altered photographs

•Modified dates of birth

•Tampered visa stamps

•Identity impersonation

•Multiple identities used by the same person Expired or blacklisted travel documents

•High passenger volume causing delays Current verification methods rely heavily on human inspection and basic database lookups.

•Detailed Description Border checkpoints process thousands of identity documents every day,including passports, visas, national identity cards, permits, and travel authorizations. Manual verification is time-consuming, prone to human error, and often unable to detect sophisticated forgeries, tampering, or identity fraud.Develop an Al-powered document screening platform that automatically analyzes identity and travel documents, detects signs of tampering or forgery, validates information against rules and databases,and generates a risk score to assist border security personnel in making faster and more accurate decisions.

•Expected Solution

•Module 1: OCR Extraction

•Module 2: Document Validation

•Module 3: Tampering Detection

•Module 4: Face Detection Module 1: OCR Extraction Objective: Automatically extract all relevant information from identity documents.

Inputs:

•Passport image

•Visa image

•National ID image

•Driving license

•Permit documents Extracted Fields:

Passport

•Name

•Passport Number

•Nationality

•Date of birth

•Date of expiry

•Gender Visa

•Visa Number

•Visa Type

•Entry Validation

•Stay Duration Module 2: Document Validation Objective: Verify whether the extracted information follows official document standards.

Module 3: Tampering Detection (Core AI Innovation)

OBJECTIVE

Detect digitally or physically altered documents.

Use Cases:

•Photo Replacement

•Text Manipulation

•Stamp Forgery Detection

•Image Metadata Analysis Module 4: Face Verification Objective: Ensure document owner matches the presented individual.

•Expected Impact

•Reduce document verification time from several minutes to a few seconds.

•Improve detection of forged and tampered documents.

•Standardize screening decisions across checkpoints.

•Enable data-driven risk assessment instead of purely manual inspection.

•Create a digital trail for investigations and intelligence analysis.

Possible Project Name Al-Based Fake Identity & Document Screening System.