Assessfy Pvt. Ltd Moderate 5 milestones 100 marks

AI Photo Finder by Face (Event Photo Retrieval)

Target year: TE Sem 5-6 (Mini-Project-IIA/IIB) AICTE: 3 credits · ~75 hrs Bloom: Analyze MU CBCS: CSC602/CSC702 Mini-Project 2A/2B Powered by: AI Products Factory (PhotoFinder AI)

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 web app where users upload one selfie + a folder of event photos, and the AI returns every photo containing that person's face. Uses FaceNet/ArcFace embeddings + FAISS vector search. Target use case: wedding photographers, school events, sports days — automatically deliver each attendee their photos. Direct clone of PhotoFinder AI's value proposition.

Course Learning Outcomes (CLOs):
CLO1: Apply face embedding models to convert images into searchable vectors.
CLO2: Build a vector-search index using FAISS.
CLO3: Design a REST API for image upload + face-match retrieval.
CLO4: Evaluate retrieval accuracy at top-K = 5, 10, 20.
CLO5: Reason about scale: how would this work for a million photos?

Industry/societal relevance: PhotoFinder AI (an AI Products Factory product) is used by wedding photographers + event organizers across India. Indian wedding industry alone is $50B+ — direct B2B SaaS revenue opportunity.

Milestones

1. Dataset + Folder Structure

15 marks 7d

Collect 100+ test photos with known identities (use a free dataset like CelebA subset). Document structure.

2. Face Detection + Embedding

20 marks 14d

For each photo, detect faces + compute embeddings. Store as .npy + a manifest CSV.

3. FAISS Index + Query

25 marks 14d

Build FAISS index on all embeddings. Query: given a selfie embedding, return top-K matching photo IDs.

4. Web UI

20 marks 18d

Streamlit/React app: upload selfie + folder, see matches with similarity %. Download all matched photos as ZIP.

5. Evaluation + Demo Video

20 marks 18d

Measure precision@10 on labelled test set. Record 5-min demo. 8-page report.

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.

AI Photo Finder by Face

AI Products Factory · Remote · 12w

Certificate of Completion 2 of 2 seats

Develop face-based photo retrieval for PhotoFinder AI at 1M+ photo scale. You will own the embeddings + vector-index pipeline: extract FaceNet/ArcFace embedd...

Apply now

Skills you'll learn

PythonFace Embeddings (FaceNet / ArcFace)Vector Search (FAISS)Flask/FastAPIReact or StreamlitImage handling (PIL/Pillow)Cosine similarityPre-trained model deployment

Tools used

Python 3.11face_recognition or DeepFaceFAISS (CPU build)FastAPIReact (or Streamlit for MVP)PillowDockerGitHub

Prerequisites

Python intermediate; basic linear algebra (vectorscosine similarity); intro to deep learning + pre-trained models

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

AI Photo Finder by Face (Event Photo Retrieval)

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.

Moderate

AI Photo Finder by Face (Event Photo …

Assessfy

Auto-issued on completion One-click LinkedIn add