README.md

metadata

title: FeatureLab
emoji: 🐠
colorFrom: gray
colorTo: pink
sdk: gradio
sdk_version: 5.49.1
app_file: app.py
pinned: false
license: mit
short_description: Minimal feature-detection with Classical and Deep Learning

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

FeatureLab Mini — Classic & DL Detectors

FeatureLab now exposes a production-friendly layout: FastAPI serves the detector runtime over HTTP/WebSocket while Gradio rides on top for internal demos.

Runtime Overview

FastAPI (/v1/detect/*)  <-- shared numpy/CV runtime -->  Gradio UI (/)

• Classical path: Canny, Harris, Probabilistic Hough, Line Segment Detector (LSD), contour-based ellipse fitting.
• Deep path: ONNX models (HED, SuperPoint, SOLD2, etc.) auto-loaded from ./models.
• Responses: base64 PNG overlays, rich feature metadata, timings, model info.

Run locally

python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
python app.py  # FastAPI + Gradio on http://localhost:7860

HTTP API

• POST /v1/detect/edges|corners|lines|ellipses
• Body:

  {
    "image": "<base64 png/jpeg>",
    "params": {
      "canny_low": 50,
      "canny_high": 150,
      "line_detector": "lsd",
      "...": "..."
    },
    "mode": "classical|dl|both",
    "compare": false,
    "dl_model": "hed.onnx"
  }
  

• Response:

  {
    "overlay": "<png base64>",
    "overlays": { "classical": "...", "dl": "..." },
    "features": { "classical": {...}, "dl": {...} },
    "timings": { "classical": 7.2, "dl": 18.5, "total": 25.7 },
    "fps_estimate": 38.9,
    "model": { "name": "opencv-classical", "version": "4.10.0" },
    "models": { "classical": {...}, "dl": {...} }
  }
  

• Classical line detector toggle: set params.line_detector to "lsd" to run OpenCV's Line Segment Detector instead of Probabilistic Hough.
• Multipart uploads: POST /v1/detect/<detector>/upload with file, optional params (JSON string), mode, compare, dl_model.

WebSocket API

• Connect to /v1/detect/stream.
• Send JSON payloads with the same shape as HTTP.
• Receive the detection response for each frame — suitable for webcam or live sources.

Gradio Demo

• Still bundled for quick experiments (webcam capture, parameter sliders).
• Fully decoupled: the UI calls the same runtime, so React/Tauri front-ends can swap in later without touching detector code.

Deploying

• Hugging Face Spaces (Gradio) still works — FastAPI runs inside the Space process.
• For container/desktop targets, run uvicorn app:app or embed the FastAPI router into your existing service.

GPU/Core ML acceleration (ONNX) is optional; drop models into ./models to enable DL paths. Continuous upgrades toward Core ML / PyTorch backends can reuse the same API surface.