Timeline for is K-Means clustering suited to real time applications?
Current License: CC BY-SA 3.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 9, 2017 at 17:26 | comment | added | S.E.K. | @user7019377 Thank you for your detailed answer, but Jake Westfall has a point. When I said "segment a sequence of RGB images" I meant segment each image independently from the other images by clustering areas within each image. | |
| Sep 9, 2017 at 16:10 | comment | added | David Ernst | You probably are right. But I still wouldn't do spherical kmeans clusters within an image. | |
| Sep 9, 2017 at 16:09 | comment | added | Jake Westfall | Ah... I just realized that it's a little ambiguous ("segment a sequence of images"), but you may be right! Will ask for clarification | |
| Sep 9, 2017 at 16:03 | comment | added | David Ernst | When he says he wants to segment a sequence of images I read it as clustering images with similar images, not clustering areas within each image. The points of high dimensionality would then not apply but the point about spheres would still apply. | |
| Sep 9, 2017 at 15:59 | comment | added | Jake Westfall | Maybe I'm missing something, but I don't see how having images of size 1280 x 960 makes this a 1228800-dimensional problem. Doesn't increasing the size of the image just increase the number of data points, not the dimensionality? | |
| Sep 9, 2017 at 15:23 | history | answered | David Ernst | CC BY-SA 3.0 |