PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Mini Project
Facial Emotion Detection
Classifies seven emotions from a live webcam feed
1-2 weeks build
Overview
A CNN trained on the FER-2013 dataset classifies faces into seven expressions: angry, disgust, fear, happy, sad, surprise and neutral. OpenCV finds faces in the webcam feed, the model labels each one in real time, and a small chart tracks the mood mix over a session. The report compares a scratch CNN with a fine-tuned pretrained model.
What makes it stand up
- 01Seven-class expression model trained on FER-2013
- 02Real-time labels drawn over each detected face
- 03Scratch CNN compared with transfer learning
- 04Class-imbalance handling with weights and augmentation
- 05Session mood chart and per-class F1 in the report
Module breakdown
- 01
Data
FER-2013 loading, balancing and augmentation.
- 02
Models
Custom CNN and a fine-tuned pretrained network.
- 03
Training
Curves, early stopping and checkpoints.
- 04
Live inference
Webcam loop with face detection and labels.
- 05
App
Streamlit page with session mood chart.
After this, you will be able to
- Explain convolution and pooling on a face image
- Defend how you handled the rare disgust class
- Demo live emotion labels on your own face
Technology stack
- Python
- TensorFlow
- OpenCV
- Streamlit
- Level
- Mini Project
- Domain
- Artificial Intelligence
- Build time
- 1-2 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support