README.md

metadata

title: Industrial Defect Detection
emoji: 🔍
colorFrom: blue
colorTo: gray
sdk: gradio
sdk_version: 6.0.0
app_file: app.py
pinned: false
license: other
short_description: Industrial Defect Detection API with FastAPI and Gradio UI

Industrial Defect Detection API

A unified service providing both FastAPI endpoints (for production) and Gradio UI (for testing/demo).

Features

• FastAPI Endpoints: RESTful API compatible with MonitaQC's YOLO inference format
• Gradio UI: Web interface for visual testing and demonstration
• Multiple Models: Support for 10 different defect detection models
• CPU-based: Runs on ONNX Runtime (no GPU required)
• Cloud-ready: Deployed on HuggingFace Spaces

Available Models

Each model has its own dedicated endpoint:

Model	Model Key	API Endpoint
Data Matrix	data-matrix	/v1/object-detection/data-matrix/detect
Dental Implant	dental-implant	/v1/object-detection/dental-implant/detect
Ball Pen	ball-pen	/v1/object-detection/ball-pen/detect
Knit Up	knit-up	/v1/object-detection/knit-up/detect
Knit Back	knit-back	/v1/object-detection/knit-back/detect
Jean Up	jean-up	/v1/object-detection/jean-up/detect
Jean Back	jean-back	/v1/object-detection/jean-back/detect
Tire Cord	tire-cord	/v1/object-detection/tire-cord/detect
PVB Film	pvb-film	/v1/object-detection/pvb-film/detect
Car Glass	car-glass	/v1/object-detection/car-glass/detect

Full URLs:

• Data Matrix: https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/data-matrix/detect
• Dental Implant: https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/dental-implant/detect
• Ball Pen: https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/ball-pen/detect
• Knit Up: https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/knit-up/detect
• Knit Back: https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/knit-back/detect
• Jean Up: https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/jean-up/detect
• Jean Back: https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/jean-back/detect
• Tire Cord: https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/tire-cord/detect
• PVB Film: https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/pvb-film/detect
• Car Glass: https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/car-glass/detect

API Usage

FastAPI Endpoints

Detect with Default Model:

POST /v1/object-detection/detect
Content-Type: multipart/form-data

Parameters:
  - image: file (required)
  - model: string (optional, default: data-matrix)
  - confidence: float (optional, default: 0.25)

Detect with Specific Model:

POST /v1/object-detection/{model_name}/detect
Content-Type: multipart/form-data

Parameters:
  - image: file (required)
  - confidence: float (optional, default: 0.25)

Example:

curl -X POST "https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/data-matrix/detect" \
  -F "image=@test.jpg" \
  -F "confidence=0.25"

Response Format:

[
  {
    "bbox": [x1, y1, x2, y2],
    "confidence": 0.85,
    "class_id": 0,
    "x1": 100.0,
    "y1": 150.0,
    "x2": 200.0,
    "y2": 250.0
  }
]

Integration with MonitaQC

1. Open MonitaQC status page: http://localhost:5050/status
2. Go to "Infrastructure Configuration"
3. Update YOLO URL to: https://smartfalcon-ai-industrial-defect-detection.hf.space/v1/object-detection/data-matrix/detect
4. Click "Set URL"

Documentation

• API Docs: /docs
• Health Check: /health
• List Models: /models