# DeepFace Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/deepface
> Markdown URL: https://aitinkerers.org/technologies/deepface.md
> Technology record last updated: 2026-07-27T07:18:54Z
> Generated: 2026-09-23T05:38:37Z

DeepFace is a lightweight, open-source Python library for advanced facial recognition and attribute analysis.

DeepFace is a robust, open-source Python library designed for comprehensive facial recognition and attribute analysis. It wraps state-of-the-art deep learning models (like VGG-Face, FaceNet, and OpenFace) into a single, easy-to-use API, allowing developers to perform tasks such as face verification, identification within a database, and analysis of attributes like age, gender, emotion, and race. The framework handles complex stages of the facial recognition pipeline—detection, alignment, normalization, representation, and verification—in the background, simplifying implementation. DeepFace has achieved accuracy levels comparable to, and sometimes surpassing, human performance on facial recognition tasks, making it a powerful tool for various AI applications.

- Official technology site: https://github.com/serengil/deepface
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Edge-AI Kindergarten Attendance: Automating Check-ins with Computer Vision & Local LLM Workflows](https://wellington.aitinkerers.org/talks/rsvp_s0e9vu8YVco)

I built an automated, privacy-first facial recognition attendance system for daycares to replace manual paper check-in logs, utilizing a local Python, OpenCV, DeepFace, Flask, and SQLite stack. To bridge computer vision with generative AI, the system integrates a local open-weights LLM via Ollama and Qwen. During the live demo, I will showcase how real-time camera frames trigger automated face verification, log attendance locally into SQLite, and instantly invoke the local LLM endpoint (/api/ai-summary) to generate professional natural language daily attendance reports, pattern summaries, and administrative notes completely offline. Example Pipeline & Output: The system serializes recent database rows into a structured markdown text log (e.g., - Time: 10:05:05 | Guardian: Mahesh Endla | Child: Hrithvik Endla) and passes it through strict prompt constraints. This produces professional markdown reports featuring daily attendance patterns, anomaly flags, and administrative notes: Markdown **Daily Summary Report** **Date:** August 11, 2026 **Attendance Patterns:** Today was a busy day with multiple check-ins for Hrithvik Endla at approximately 10:05 AM by his guardian, Mahesh Endla. **Administrative Note:** Please confirm with the guardian regarding check-in frequency to ensure records are accurately reflected.

- Event context: AI Tinkerers Wellington: Inaugural Meetup · 26 August 2026 — 2026-08-26 — Wellington
- Public talk page: https://wellington.aitinkerers.org/talks/rsvp_s0e9vu8YVco

### [EduSense: A Multi-Agent AI Platform for Emotion-Aware Education](https://dubai.aitinkerers.org/talks/rsvp_KyNKCO_MVFc)

EduSense is a multi-agent AI education platform built for the Kaggle AI Agents Capstone. It uses DeepFace for real-time facial emotion analysis via webcam, and 7 specialized agents — orchestrated by a central workflow — to generate lessons, quizzes, flashcards, and PDF reports for instructors. The backend runs on FastAPI with PostgreSQL. I'll demo the live agent pipeline: emotion capture, the sequential agent workflow, and the instructor dashboard.

- Event context: AI Tinkerers Dubai — August Demo Day — 2026-08-08 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_KyNKCO_MVFc

## Related Technologies

- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos
- [Flask](https://aitinkerers.org/technologies/flask) ([Markdown](https://aitinkerers.org/technologies/flask.md)) — 24 public demos
- [Gemini API](https://aitinkerers.org/technologies/gemini-api) ([Markdown](https://aitinkerers.org/technologies/gemini-api.md)) — 20 public demos
- [Ollama](https://aitinkerers.org/technologies/ollama) ([Markdown](https://aitinkerers.org/technologies/ollama.md)) — 77 public demos
- [OpenCV](https://aitinkerers.org/technologies/opencv) ([Markdown](https://aitinkerers.org/technologies/opencv.md)) — 26 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 106 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 664 public demos
- [SQLite](https://aitinkerers.org/technologies/sqlite) ([Markdown](https://aitinkerers.org/technologies/sqlite.md)) — 28 public demos