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 · Major Project
Blood Cell Detection & Counting
Detects and counts RBCs, WBCs and platelets in blood smear images
2-3 weeks build
Overview
Trains a YOLOv8 detector on the public BCCD dataset to box red cells, white cells and platelets in stained smear images, then counts each type per field. A classical OpenCV watershed baseline is included for comparison, and the web app returns an annotated image with a count table.
What makes it stand up
- 01BCCD smear images with bounding-box labels for three cell types
- 02YOLOv8 fine-tuning with mAP and per-class precision and recall
- 03Watershed segmentation baseline for a classical comparison
- 04Handling of overlapping red cells in dense fields
- 05Academic lab-assist prototype, not a certified haematology counter
Module breakdown
- 01
Dataset
Annotation conversion to YOLO format and train-val splits.
- 02
Detector
YOLOv8 training with tuned anchors and augmentation.
- 03
Classical baseline
Colour thresholding and watershed cell separation.
- 04
Counting
Per-class counts with confidence and overlap filtering.
- 05
Web app
Upload, annotated output and exportable count report.
After this, you will be able to
- Explain how single-stage detectors predict boxes and classes
- Defend deep learning against the watershed baseline with results
- Demo counting on a fresh smear image
Technology stack
- Python
- YOLOv8
- OpenCV
- Flask
- React
- Level
- Major Project
- Domain
- Artificial Intelligence
- Build time
- 2-3 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