Book Spine Detection with YOLOv8
YOLOv8n object detection model trained to detect book spines.
Model Details
- Architecture: YOLOv8n
- Task: Object Detection
- Image Size: 416 × 416
- Epochs: 50
- Batch Size: 8
Performance
| Metric | Score |
|---|---|
| Precision | 0.954 |
| Recall | 0.912 |
| mAP@50 | 0.965 |
| mAP@50-95 | 0.813 |
Usage
Install Ultralytics:
pip install ultralytics
Download the best.pt file from this repository.
Python
from ultralytics import YOLO
# Load the trained model
model = YOLO("best.pt")
# Run inference
results = model("image.jpg")
# Display results
results[0].show()
Command Line
yolo detect predict model=best.pt source=image.jpg
The model returns bounding boxes, confidence scores, and class predictions for detected book spines.
Limitations
- Performance may vary with lighting, camera angle, image quality, and background.
- Small, blurry, or heavily occluded book spines may be difficult to detect.
- Performance may decrease on images that differ significantly from the training data.
Intended Use
This model is intended for book-spine detection in computer vision experiments, research projects, and prototype applications.
License
Please add the appropriate license for your model and dataset.
- Downloads last month
- -