Timeline for Statistical measure for if an image consists of spatially connected separate regions
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 27, 2013 at 4:54 | comment | added | EngrStudent | Sorry for the double comment. I think it is "clever" to use part of an object as a pseudo "mother-wavelet" for itself. It seems self referential, but also poetic. Self Adjoint. | |
| Mar 27, 2013 at 4:52 | comment | added | whuber♦ | Thanks! So it looks like you are in a great position to flesh out this answer and demonstrate how effective it really is. :-) | |
| Mar 27, 2013 at 4:48 | comment | added | EngrStudent | It is from my Thesis. (Mechanical Engineering) I put a Gaussian blur on the position of a nonlinear pendulum, and then used the convolution method to back out the position from an image and compare it to the analytic. I tried it with several levels of noise. As long as the noise was below a threshold related to the size of the gaussian, there was very good reconstruction. link Figure 11 was the relevant graph for the reconstruction. Figure 6 and equation 2 indicate response to noise. | |
| Mar 26, 2013 at 15:43 | comment | added | whuber♦ | Some interesting ideas here! Could I persuade you to flesh out this answer by applying one or more of your approaches to the sample images to (1) show how your methods work and (2) evaluate how well they perform? | |
| Mar 26, 2013 at 4:53 | history | answered | EngrStudent | CC BY-SA 3.0 |