Timeline for Detect clusters in an RGB space
Current License: CC BY-SA 3.0
9 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Apr 12, 2018 at 22:35 | vote | accept | TJA | ||
Apr 11, 2018 at 10:50 | answer | added | A_A | timeline score: 0 | |
Apr 11, 2018 at 9:29 | comment | added | TJA | The idea behind using a 3D space where the axes are R, G, B is that that the grey's will be relatively close to a line from black(0, 0, 0) to white(256, 256, 256) well actually more like (80, 80, 80) whereas the blue biro and brown water stains would be off to the side. The reason I refer to clusters is that I expect to see groups of similar colours forming clusters within that space. And by working from the notional centre of these clusters I can include/exclude surrounding colour points from each of those sets. | |
Apr 11, 2018 at 9:18 | comment | added | TJA | So the main objective is the "binarization" of the images into just black and white values before using various elements of the OpenCV or similar libraries. | |
Apr 10, 2018 at 7:39 | comment | added | A_A | No worries. I was wondering if it would be possible to clarify how you see this working conceptually because the phrase "... I would like to take advantage of the essentially 3D nature of RGB colour vs 2D grayscale images to improve the accuracy..." draws a comparison between two dissimilar things, the image and the colour space. I suppose that your objective is to "filter" only what appears to be grayscale from an image (?). | |
Apr 10, 2018 at 1:48 | comment | added | TJA | @A_A thanks for the tidy up didn't know you could do that. | |
Apr 10, 2018 at 0:17 | history | edited | A_A | CC BY-SA 3.0 |
URL formating
|
Apr 9, 2018 at 22:46 | review | First posts | |||
Apr 10, 2018 at 0:33 | |||||
Apr 9, 2018 at 22:44 | history | asked | TJA | CC BY-SA 3.0 |