Timeline for Preprocess image data to classify objects based on shape
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 16, 2020 at 11:08 | history | edited | CommunityBot |
Commonmark migration
|
|
| Apr 6, 2019 at 17:16 | comment | added | Equintox | thanks i will check it out :) | |
| Apr 5, 2019 at 16:59 | comment | added | Pedro Henrique Monforte | Check this video: youtube.com/… | |
| Apr 5, 2019 at 16:57 | history | edited | Pedro Henrique Monforte | CC BY-SA 4.0 |
added 545 characters in body
|
| Apr 5, 2019 at 16:34 | comment | added | Equintox | This is why i tried to do it with my approach of cropping out each bottle and split them into a 2d array of tiles (e.g. 50x20). For every Tile i execute a PCA which gives me the direction of the line of the tile. So in the end it doesnt matter if it is a big or small bottle or if my input img is 5000px or only 400px as the output of any is a 50x20 array of vectors | |
| Apr 5, 2019 at 13:38 | comment | added | Pedro Henrique Monforte | That is a problem, since size is relevant part of this classification problem. You have to use really detailed shape information | |
| Apr 5, 2019 at 13:34 | comment | added | Equintox | Thanks a lot for all these great and helpful tips. I will read myself into these topics and try it out. With my approach the sizes actually don't matter as i split each image into a 2d tile array of the same size. | |
| Apr 4, 2019 at 21:59 | history | answered | Pedro Henrique Monforte | CC BY-SA 4.0 |