What do you recommend for recognizing squares in an image?

The data needed to know is:

  • Identify concrete squares.

  • Identify the pixel coordinates of (the edges of) the squares in the image.

A couple of examples:

  • 20 squares identified.
  • For each square identify its pixel coordinates.

enter image description here

  • 2 squares identified.
  • First square coordinates: (38, 124, 86, 187).
  • Second square coordinates: (88, 124, 136, 187).

enter image description here

  • $\begingroup$ Hi @Lesair Valmont, is the square always white and have the same ratio (width : length)? $\endgroup$ – malioboro Jun 18 '19 at 22:28
  • $\begingroup$ Squares' fill color is always white. Squares' ratio may vary. $\endgroup$ – Lesair Valmont Jun 19 '19 at 17:22
  • $\begingroup$ Do you have any constraint on detection time? How much data do you have? $\endgroup$ – firion Jun 21 '19 at 14:58
  • $\begingroup$ No time constraints. About 1,000 images. $\endgroup$ – Lesair Valmont Jun 29 '19 at 11:58

You might want to look into building convolutional neural network (CNN) for object detection using Keras. With plain white squares, it should work pretty good.

  • $\begingroup$ Can you elaborate a little more about Keras with Azure? $\endgroup$ – Lesair Valmont Jun 24 '19 at 16:36
  • $\begingroup$ I have very little experience with Azure. But if you are not familiar with CNNs in general, check the following coursera course coursera.org/learn/convolutional-neural-networks? $\endgroup$ – serali Jun 24 '19 at 17:26

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.