Views
No views yet
Automated detection and classification of microplastics from microscopy images. Developed for industrial deployment at IZONICS — achieving >90% accuracy in production.
| Property | Details |
|---|---|
| 🏗️ Architecture | YOLOv5 |
| 🎯 Task | Object Detection + Classification |
| 📊 Accuracy | >90% in production |
| ⚡ Speedup | 30% faster than classical image processing pipeline |
| 🏭 Deployment | Fully industrialized — prototype to production |
| ⚙️ Framework | PyTorch |
| 📜 License | MIT |
| Metric | Score |
|---|---|
| Production accuracy | >90% |
| Processing speedup vs. classical pipeline | 30% |
| Deployment status | ✅ Fully industrialized |
1import torch
2
3# Load the model
4model = torch.hub.load("ultralytics/yolov5", "custom", path="best.pt")
5model.conf = 0.35 # confidence threshold
6
7# Run inference
8results = model("microscopy_image.jpg")
9
10# Show results
11results.show()
12
13# Get detections as dataframe
14df = results.pandas().xyxy[0]
15print(df)