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
Fruit Freshness Detection
Classifies apples, bananas and oranges as fresh or rotten from a photo
1-2 weeks build
Overview
A compact quality-check tool built on the public Fruits Fresh and Rotten dataset on Kaggle. A MobileNetV2 backbone is fine-tuned to recognise both the fruit and its condition, and a Flask page accepts an upload or webcam frame and returns the label. The report includes a confusion matrix and per-class F1 so misclassifications are easy to discuss.
What makes it stand up
- 01Six-class model covering three fruits in fresh and rotten states
- 02Lightweight MobileNetV2 backbone that runs on a laptop CPU
- 03Augmentation for lighting and angle changes seen in real shops
- 04Webcam capture as well as file upload
- 05Confusion matrix and per-class F1 in the report
Module breakdown
- 01
Dataset
Kaggle download script, cleaning and stratified splits.
- 02
Model
Fine-tuned MobileNetV2 with a small dense head.
- 03
Augmentation
Brightness, rotation and flip transforms during training.
- 04
Web app
Flask page with upload and webcam capture.
- 05
Evaluation
Confusion matrix, per-class F1 and misclassified samples.
After this, you will be able to
- Explain how a pretrained backbone speeds up a small project
- Discuss which classes get confused and why
- Demo freshness checks on real fruit during the viva
Technology stack
- Python
- TensorFlow
- OpenCV
- Flask
- 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