GitHub

Reference

CounterMarking.density_map — Method
nmarked = density_map(jldfile::AbstractString)

Given a JLD2 file jldfile written by gui, return an array nmarked counting of the number of images with a urine spot in each pixel. Before counting, the images are flipped so that the stimulus segment is in the upper left corner.

source
CounterMarking.gui — Method
gui(outbase, files)
gui(outbase, glob::GlobMatch)

Run the graphical user interface (GUI) for CounterMarking. Supply the base name of the output files (e.g., "my_results") and a list of image files to process (alternatively, supply a glob"pattern" that matches just the files you want to process).

The GUI will display the images and their segmentation, and allow the user to select the segments corresponding to the stimulus (yellow) and marked spots. The results will be save to:

  • outbase.xlsx: an Excel file with one sheet per image, containing summary statistics on the stimulus spot and the selected spots.
  • outbase.jld2: a JLD2 file with one dataset per image, containing the segmented image, the selected spots, and the stimulus segment.

The JLD2 file can be used by density_map.

source
CounterMarking.meanshow — Function
meanshow(seg; kwargs...)
meanshow(img, seg; kwargs...)

Display a segmented image using the mean color of each segment. The version with img displays the original image and the segmented image one atop the other, and zooming on one will zoom on the other.

Note

You must load the ImageView package to use this function.

source
CounterMarking.process_images — Method
process_images(outfile::AbstractString, glob::GlobMatch; dirname=pwd())
process_images(outfile::AbstractString, glob::AbstractString; dirname=pwd())

Process all images with filenames matching glob and save the results to outfile. Each image will be a separate sheet in the Excel file.

Optionally specify the dirname containing the images.

Examples

To process a collection of images in a different directory, and save the results to that same directory:

julia> process_images("2025-03-15/results.xlsx", glob"*.png"; dirname="2025-03-15")
source
CounterMarking.randshow — Function
randshow(seg; kwargs...)
randshow(img, seg; kwargs...)

Display a segmented image using random colors for each segment. The version with img displays the original image and the segmented image one atop the other, and zooming on one will zoom on the other.

!!! note You must load the ImageView package to use this function.

source
CounterMarking.segment_image — Method
seg = segment_image(img; threshold=0.1, min_size=20)

Given an image img, segment it into regions using a region growing algorithm. min_size is the minimum number of pixels per segment, and threshold determines how different two colors must be to be considered different segments. Larger threshold values will result in fewer segments.

source
CounterMarking.spots — Method
spotdict, stimulus = spots(seg; max_size_frac=0.1)

Given a segmented image seg, return a Dict(idx => spot) where idx is the segment index and spot is a Spot object where spot.npixels is the number of pixels in the segment and spot.centroid is the centroid of the segment.

stimulus is a Pair{Int, Spot} where the first element is the index of the stimulus segment and the second element is the Spot object for that segment.

Spots larger than max_size_frac * npixels (default: 10% of the image) are ignored.

source
CounterMarking.stimulus_index — Function
idx = stimulus_index(seg::SegmentedImage, colorproj = RGB(1, 1, -2))

Given a segmented image seg, return the index of the segment that scores highest on the product of (1) projection (dot product) with colorproj and (2) number of pixels.

source
CounterMarking.upperleft — Method
spotdict_ul, stimulus_ul = upperleft(spotdict::AbstractDict{Int, Spot}, stimulus, imgsize)

Given a spotdict of Spot objects and a stimulus segment, return a new spotdict_ul corresponding to an image flipped so that stimulus_ul is in the upper left corner.

source