My assignment is to measure images of biological specimens resting on a 2-D scale. An example of such an image is shown here.
I've drawn as much as possible from an article from PyImageSearch: https://pyimagesearch.com/2016/03/28/measuring-size-of-objects-in-an-image-with-opencv/
In the article, the author explores using the CV2 package from OpenCV to measure a number of simple objects by comparing to a reference object of known dimensions. In a sense, my assignment is both simpler (it's resting on top of the scale), and more difficult (the shapes are much more complex).
Essentially, I want to look for ways to locate the 1 cm x 1 cm "blocks" on the scale background and use them to obtain a measurement for the specimen. Even if the measurement is not perfect because of 3D, I could then apply a training-testing algorithm to amend my assessment.
What I'm asking is, is there an easy way to identify an unobstructed 1x1 block on the scale and assign it as the reference object? And is there a reliable way to take the measurement, presumably using the greyscale color differential, of the large specimen? Thanks.