This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
Transformation that was applied to objects in photo is combination of perspective transform with some deformation that come from lens. So affine transform (also called weak perspective transform) is not enough. On other hand if you are using only 4 points, you can't compute anything that is more complicate that perspective transform (there just not enough information). So you should use perspective transform for your task, and hope that other deformations are not very significant.
