0

Hi I have the following heat map (probability map) of an object. enter image description here How can I convert this heatmap to a binary image? I want to take the maximum area of the object to increase the intersection with the image in the right side. I really appreciate any help.

S.EB
  • 1,966
  • 4
  • 29
  • 54
  • Use matplotlib's [`savefig()`](https://matplotlib.org/devdocs/api/_as_gen/matplotlib.pyplot.savefig.html)... – zwer Jun 10 '17 at 00:50

1 Answers1

0

To binarize, compare against a threshold:

thresh = 0.5
bin_map = prob_map > thresh

From there you can use a very large variety of solutions:

Saving a numpy array as an image

I recommend this one from migas:

from PIL import Image
im = Image.fromarray(A)
im.save("your_file.jpeg")