 | 1 | initial version |
Hi, i'm working with SIFT feature and need some information about th descriptor. In the origanal paper they say that th descriptor use a window of the size 16x16 around a keypoint with 4x4 subregions. My question is if they mean 16x16 pixel? Or is the size(in pixel) of the window depending on the scale? Furthermore are the descriptors calculated in the gaussian image or at the original?
| | 2 | No.2 Revision |
Hi,
i'm working with SIFT feature and need some information about th descriptor. In the origanal paper they say that th the descriptor use a window of the size 16x16 around a keypoint with 4x4 subregions. My question is if they mean 16x16 pixel? Or is the size(in pixel) of the window depending on the scale? Furthermore are the descriptors calculated in the gaussian image or at the original?
| | 3 | No.3 Revision |
Hi,
i'm working with SIFT feature and need some information about th the descriptor. In the origanal paper they say that the descriptor use a window of the size 16x16 around a keypoint with 4x4 subregions. My question is if they mean 16x16 pixel? Or is the size(in pixel) of the window depending on the scale? Furthermore are the descriptors calculated in the gaussian image or at the original?
| | 4 | No.4 Revision |
Hi,
i'm working with SIFT feature and need some information about the descriptor. In the origanal paper they say that the descriptor use a window of the size 16x16 around a keypoint with 4x4 subregions. My question is if they mean 16x16 pixel? Or is the size(in pixel) of the window depending on the scale? Furthermore are the descriptors calculated in the gaussian image or at the original?And if yes, how??
