Closed matthaeusheer closed 4 years ago
Since there will be distortion in the image, the idea is to pick (detect) four points, e.g. some features in some color in the corners, and chose those four points to perspectively distort the image to for rectification. See https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_imgproc/py_geometric_transformations/py_geometric_transformations.html. This would potentially also solve the scaling issue since one could scale the image according to the known landmarks.
Since there will be distortion in the image, the idea is to pick (detect) four points, e.g. some features in some color in the corners, and chose those four points to perspectively distort the image to for rectification.
See https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_imgproc/py_geometric_transformations/py_geometric_transformations.html.
This would potentially also solve the scaling issue since one could scale the image according to the known landmarks.