Page "Scale-invariant feature transform" Paragraph 4

Another important characteristic of these features is that the relative positions between them in the original scene shouldn't change from one image to another.

For example, if only the four corners of a door were used as features, they would work regardless of the door's position ; but if points in the frame were also used, the recognition would fail if the door is opened or closed.

Similarly, features located in articulated or flexible objects would typically not work if any change in their internal geometry happens between two images in the set being processed.

However, in practice SIFT detects and uses a much larger number of features from the images, which reduces the contribution of the errors caused by these local variations in the average error of all feature matching errors.