0

I have read all that staff about image similarity index on that forum but i think that my subject is kind different because images that i want to compare comes from an L-system generator and as you can see bellow it's hard to find obvious differences. So i couldn't decide which method and software to choose for my problem.

But let's take the story from the beginning. I have a collection of data , by measuring angles and lengths of branches of some plants (15 in total), and i represented them with L-system fractals method as already told.

These images looks like the above ones:

enter image description here Plant A enter image description here Plant B enter image description here Plant C

Till now i tried to find differences using two methods.

1) By calculating the fractal dimension of those images but as expected, it was 2 in all of them

2) By calculating the % of area coverage in a same canvas. Numbers in that case show some differences but there are not statistically significant.

So the thought was to use an other similarity index but there are too many protocols and ideas out there that i couldn't find a starting point. I read about OPENCV , VisualCI etc but because i've never used such methods again, i feel somehow lost.

Any of your suggestions will be welcome.

Thank you.

F.N
  • 401
  • 4
  • 21
  • I am sorry but what is exactly the question? And I am not sure that fractal dimension of the shown images is two - for example [3-branches tree](http://en.wikipedia.org/wiki/List_of_fractals_by_Hausdorff_dimension) has fractal dimension of ~1.58. – NightElfik Mar 11 '15 at 03:37
  • Actually using box counting method for fractal dimension in matlab , fractal dimension of these images are close enough to 2. (i mean 1.9856 e.g). So the question is if i can compare those images with another way. For example to say that plant B is more close to plant C than plant A or something like that. – F.N Mar 11 '15 at 09:12
  • Are they produced by the same L-systems? In that case you might want to estimate the parameters (angles, lengths) and compare those. If your trees split to two smaller branches every iteration ten the dimension `D = -log(4)/log(1/2) = 2` as you measured (not counting overlapping), so that probably won't help you as you correctly deducted. – NightElfik Mar 11 '15 at 15:51
  • Yeah sure. i can make a comparison on the angles and lengths but i also i want to try and a different approaching way through image analysis (if there is any) and that's why i'am asking here. – F.N Mar 11 '15 at 20:45
  • After some more research, i conclude to use DTW method. – F.N Mar 19 '15 at 19:47

0 Answers0