-2

I am hoping that TensorFlow can turn this input, to this output.

Input: A floorplan PNG, and 1 - 5 images of a symbol

Output: The same floorplan, but with all matching symbols highlighted

I can do the hard work of figuring out HOW to do it, but I don't want to waste 2 weeks just to figure out it wouldn't be possible. I know I'd need to train it with multiple images, but I won't have more than 5 examples of a given symbol.

Does TensorFlow have these capabilities?

Thanks!

Matthew Fishman
  • 23
  • 7

1 Answers1

0

Yes, it is possible to use tensorflow to create a machine learning algorithm to do that for you, but I would bet that is not how you want to do this. First off, in order to do this in tensorflow, you would need to manually create a large number of training samples and spend a significant amount of time figuring out how to define the network and train it. Sure, you could do it, but I definitely wouldn't advise it.

If you have a specific set of symbols that you want to highlight, it would probably be better to use opencv to find and highlight the symbols. For example, in opencv, you could use Template Matching to find a specific symbol in the floor plan and then highlight them by modifying pixel color.

Bren077s
  • 152
  • 1
  • 2
  • 8
  • I know "recommendations" aren't encouraged here, but are there other algorithms worth implementing, to compare performance against the Template Matching algorithm? – Matthew Fishman May 22 '17 at 15:33
  • I do not know anything specific personally, but [this thread](https://stackoverflow.com/questions/22319867/what-is-the-best-method-to-template-match-a-image-with-noise) seems to address the issue to some extent. To be fair, you could train a few basic models in tensorflow(or any other machine learning library) and see how they do. They might end up having better performance. – Bren077s May 22 '17 at 15:45
  • _Template matching_ wouldn't world well in this context as it will not be able to recognize a (affine) transformed version of a given symbol. I recommend you to have a look at [**Feature Matching**](http://docs.opencv.org/trunk/dc/dc3/tutorial_py_matcher.html) instead. – Elouarn Laine May 22 '17 at 16:31
  • @ElouarnLaine in plain simple binary image there is no features – Yu Da Chi Feb 20 '20 at 08:11