Triangle Auto Threshold

Creates a binary image from a gray image using adaptive thresholding.

plantcv.threshold.triangle(gray_img, object_type="light", xstep=1)

returns thresholded/binary image

  • Parameters:
    • gray_img - Grayscale image data
    • object_type - "light" or "dark" (default: "light"). If object is lighter than the background then standard thresholding is done. If object is darker than the background then inverse thresholding is done. The threshold is searched for on the object's side of the histogram peak: above the peak for "light", below it for "dark". If the peak is already at that end of the histogram (for example, a dark object on a background masked to 0), there is nothing to search and an error is raised.
    • xstep - Value to move along x-axis to determine the points from which to calculate distance recommended to start at 1 (default) and change if needed.
  • Context:
    • Used to help differentiate plant and background

Grayscale image (green-magenta channel)

Screenshot


from plantcv import plantcv as pcv

# Set global debug behavior to None (default), "print" (to file), 
# or "plot" (Jupyter Notebooks or X11)
pcv.params.debug = "plot"

# Create binary image from a gray image based
thresholded = pcv.threshold.triangle(gray_img=gray_img, object_type='light', xstep=10)

Triangle Auto-Thresholded image (xstep=10)

Screenshot

Screenshot


# Create binary image from a gray image based 
thresholded = pcv.threshold.triangle(gray_img=gray_img, object_type='light', xstep=1)

Triangle Auto-Thresholded image (xstep=1)

Screenshot

Screenshot

Source Code: Here