Assessfy Pvt. Ltd Advanced 5 milestones 100 marks

Face Recognition Exam Proctor with Random-Interval Verification

Target year: BE Sem 7-8 (Major Project Phase-I/II) AICTE: 6 credits · ~150 hrs Bloom: Create / Evaluate MU CBCS: CSC801 / CSDLO8021 BE Project Powered by: AI Products Factory (Aarakshak)

Real-world project · AICTE-aligned · AI-graded · Audit-ready certificate

Enroll as Student Mentor this project

Milestones

Available mentors

Enrolled students

Core skills

About this project

Build a browser-based exam proctoring system that captures the student's face via webcam at random intervals (every 3-7 minutes) during an online exam, performs 1:N face match against their enrolled photo, and raises flags for: face absent, second face detected, identity mismatch. Integrates with Assessfy's existing assessment workflow. Direct extension of Aarakshak's NTA/SSC exam-verification product.

Course Learning Outcomes (CLOs):
CLO1: Apply face-detection + face-recognition fundamentals to a real-world identity-verification use case.
CLO2: Design a privacy-respectful audit-log structure (DPDP Act compliant).
CLO3: Build a full-stack web app with browser camera capture + server-side ML pipeline.
CLO4: Evaluate False Accept Rate (FAR) + False Reject Rate (FRR) on a benchmark set.
CLO5: Document the ethical + legal considerations of biometric verification in education.

Industry/societal relevance: Aarakshak (an AI Products Factory product) powers exam-proctoring for NTA / SSC / UGC-NET. Indian online-assessment market grew 300% post-COVID. Direct placement track at TestMate, MeritTrac, AICTE-empanelled testing bodies.

Milestones

1. Requirements + Privacy Note

10 marks 14d

Document use cases, threat model (impersonation / passing-camera-to-friend), DPDP-Act consent + data-retention policy. 4-page note.

2. Camera Capture + UI

20 marks 14d

Browser web-app that captures a still every 5 minutes during an exam. Live preview, consent banner, manual override.

3. Face Embedding + 1:N Match

25 marks 18d

On capture, compute face embedding, compare against enrollment vector. Threshold tuning. Report similarity score per capture.

4. Flag Engine + Audit Log

25 marks 18d

Detect: no-face, multiple-faces, identity-mismatch (similarity < threshold). Write structured audit-log to DB.

5. Evaluation + IEEE Paper

20 marks 21d

Run on 50 simulated sessions, measure FAR/FRR. Compare with cloud baseline (AWS Rekognition). 14-page IEEE-format report + oral defense.

Open internships using this project -->

Open internships using this project 1

Verified companies are actively hiring interns to work on this exact project. Apply directly.

Face Recognition Exam Proctor with Random-Interval Verification

AI Products Factory · Remote · 16w

Certificate of Completion 2 of 2 seats

Build a production-grade exam-proctor module for the Aarakshak product line. You will own random-interval webcam verification: face capture, identity match a...

Apply now

Skills you'll learn

PythonOpenCVface_recognition (dlib)Liveness fundamentalsFlask/FastAPIWebRTC + getUserMediaAWS Rekognition / Azure Face APIAudit log designDPDP Act privacy basics

Tools used

Python 3.11OpenCV 4.xdlib face_recognitionFlaskJavaScript (camera capture)AWS Rekognition or Azure Face APIMySQLGitHub

Prerequisites

Computer Vision basics; Python intermediate; one web framework (Flask/Django); basic understanding of image hashing and embeddings

Available mentors

No mentors have signed up for this project yet.

Be the first to mentor

You'll earn — Certificate (PDF)

AICTE-aligned Project Completion Certificate

A formal, audit-ready PDF certificate issued by Assessfy + your institute on successful completion. Includes AICTE credit hours, your evaluator's signature, and a QR code for third-party verification.

AICTE-aligned

Certificate of Project Completion

This is to certify that

has successfully completed the project

Face Recognition Exam Proctor with Random-Interval Verifica…

Scan to Verify

Date

Signature

Auto-issued on completion QR-verifiable

You'll earn — Digital Badge

Shareable LinkedIn / Resume Skill Badge

A compact, verifiable Open-Badges-2.0-compliant digital credential. Add to your LinkedIn profile, GitHub README, or resume in one click. Recruiters can validate authenticity via a unique URL.

Advanced

Face Recognition Exam Proctor with Ra…

Assessfy

Auto-issued on completion One-click LinkedIn add