How can I apply a function to an image to make it find figure shapes in that image ?

Hi!

I've got 3 diffirent shapes in image:

1) The red one can be described with r1 = 3-3cos(thetha) (polar coordinate system)

2) The blue one can be described with r2 = tan(sin(2*thetha)) (polar coordinate system)

3) The green one can be described with r3 = 5-4sin(2*thetha) (polar coordinate system)

So I give MatLab as in imput an image with 3 diffrent shapes, every shape can be described with it's own mathematical function (wrote about it in the begining) I've got 3 functions, and also i know how their graphs in polar coordinate look like

So now, i wanna make MatLab to work in the following way:

1) MatLab already got image with 3 different shapes as an imput;

2) I've wrote down in a live script all 3 mathematical function, that can describe my shapes in image (function's graph in polar coordinate has the same shape as the shape in image)

3) I don't understand completely how, but MatLab should do the following ( he sees a red shape in image, then he should somehow understand, that function's r1=3-3cos(thetha) graph shape is the same shape as he sees in image (the red shape in image))

4) Then he should find out that the red shape in image, can be described with r1=3-3cos(thetha) function and then he should say that red shape in image can be described with function r1=3-3cos(thetha) and tell me about this Is this possible to do as i am asking or not?

And the last thing - all these 3 shapes in image are not red/blue/green, they are grey, i've used colours in desmos just to say that there are 3 different shapes and every shape can be desctibed with it's mathematical functions ( to do that, just fo clearness, i've made them red/green/blue, so that's can't be related to a rgb image, it's just line colours in desmos)

So I’m just asking whether I can do it in deep learning toolbox, cause I’ve tried to do it in image processing toolbox and didn’t succeed, cause I know what should I do, but I completely misunderstand, even in which way should I work, like, which toolbox for example I need to choose in the beginning.

Please be patient, I’m kinda of a Matlab lamer

[Image Analyst]

What data do you have? Do you have the original x and y vectors of the curves? Or just the figures? You can get the XData and YData from the figure if that's all you have? Or do you have images with gray curves on them? I don't think you need deep learning if all you have are those three curve types. You can just look at their extent in the y direction - pretty simple. If the curves are scaled or rotated, it gets a little more complicated but it can still be done classically by examing the coordinates for things like aspect ratio or whatever.

[Greg Heath]

Does your problem include different figures that are scaled to have the same height and width?

Greg

[Dmitry Surov]

Yes, it includes different figures that are scaled to have not the exact same height and width, but I know the interval for their height and width value.

I’ve just have the figures in image, and as I understand I can get the XData and YData from the figures, using I=Imcontour(ImageName,3) for example.

This pictures is just an a example of how I wanna classify them - as I said I need to classify them in the next way - I know how function’s graph looks like in polar coordinates, and I know that this function’s graph has the same shape as one of the figures in my picture, so I need MatLab somehow to understand that function’s graph in polar coordinate has the same shape as one of the figures in the picture and tell me about this.

I think Deep learning will help me to do it, at least because I have lot’s of diffident figures

I was already told my Image Analyst to try doing it with poly2mask, but how to work further I got no ideas.

[Image Analyst]

Did you count the number of red, green, and blue pixels in the image? That should tell you. Use the Color Thresholder on the Apps tab of the tool ribbon if you need functions to get those curves. Really, it's easy - you should have solved it by now. You can do it in like 5 minutes. Just count the number of red, green, and blue pixels and whichever count is higher is the curve that it is.

[Dmitry Surov]

I’ sorry - I’ve forgot to copy from my first message that red/blue/green is just color lines, which I tried to use, to make my question clearly - like I’ve got 3 types of curves, and to match each curve’s graph to mathematical function, that describes this curve I used colors in Desmos

So in the original picture that I have to work with, all curves are grey..

Thanks for your comment