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
Garbage Classification with Deep Learning
Sorts waste photos into plastic, paper, glass, metal and organic
1-2 weeks build
Overview
Builds a waste-sorting classifier from the public TrashNet images plus an organic class from a Kaggle waste dataset. A small custom CNN is trained first as a baseline, then a fine-tuned ResNet-50 shows what transfer learning adds. A Streamlit page classifies a photo and tells the user which bin it belongs in.
What makes it stand up
- 01Five waste classes mapped to everyday bin colours
- 02Custom CNN baseline compared with a fine-tuned ResNet-50
- 03Class balancing for the under-represented categories
- 04Streamlit app with bin suggestion and confidence score
- 05Confusion matrix and per-class F1 in the report
Module breakdown
- 01
Dataset
TrashNet plus an organic class, merged and relabelled.
- 02
Baseline CNN
Three-block convolutional network trained from scratch.
- 03
Transfer model
Fine-tuned ResNet-50 with augmentation.
- 04
App
Streamlit upload and camera input with bin guidance.
- 05
Evaluation
Side-by-side metrics for both models.
After this, you will be able to
- Explain the gap between a scratch CNN and a pretrained one
- Discuss why glass and plastic get confused
- Demo sorting on rubbish photographed in the lab
Technology stack
- Python
- TensorFlow
- OpenCV
- Streamlit
- Pandas
- 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