Using OpenCV Python, How would you make all black pixels transparent, and then overlay it over original image

Question

I'm trying to make a colored mask, white. And my idea is to:

• make black pixels transparent in the mask
• merge the two images
• crop images

so then my original masked area will be white. What kind of OpenCV python code/methods would I need?

Like so:

Original

Mask

Desired result (mocked up - no green edges)

Instead of

Answer 1

I am assuming your mask is a boolean numpy array and your 2 images are numpy arrays image1 and image2.

Then you can use the boolean array as multiplier.

overlay= mask*image1 + (-mask)*image2

So you get the "True" pixels from image1 and the False pixels from image2

Answer 2

I suppose to do a color threshold to get the mask itself. The result I got in a first quick and dirty attempt with Hue 43-81, Saturation 39-197 and Brightness from 115-255 is:

The next step is a whole fill algorithm to fill the inside of the mask. Note that also one small area to the right is selected.

The next step is a substraction of the two results (mask-filled_mask):

Again fill the wholes and get rid of the noisy pixels with binary opening:

Last mask the image with the created mask.

Every step can be adjusted to yield optimal results. A good idea is to try the steps out (for example with imageJ) to get your workflow set up and then script the steps in python/openCV.

Refer also to http://fiji.sc/Segmentation .