Microscopy blob detection

Detects dark holes and the brightest blob in grayscale microscopy images.

Red circles = dark holes  |  Cyan circle = brightest blob

---

Setup

python -m pip install -r requirements.txt

Run

Place PNG images in images/, then:

python src/hole_detection.py

Results are saved to results/:

File	Description
<name>_annotated.png	Original with detection circles
<name>_mask.png	Combined binary mask
<name>_dark_mask.png	Dark holes mask
<name>_bright_mask.png	Brightest blob mask

How it works

1. Enhance — two Gaussian background-subtraction passes highlight dark holes and bright blobs separately.
2. Detect — OpenCV SimpleBlobDetector finds blob candidates in each enhanced image.
3. Filter — border blobs are discarded; top dark candidates (up to 8) and the single brightest blob are kept.
4. Annotate — detected blobs are drawn as circles on the original image and saved as masks.