Abstract: The invention relates to a method for determining deformations on an object, wherein the object is illuminated and moved while being illuminated. In the process, the object is observed by means of at least one camera and at least two camera images are generated at different times by said camera. In the camera images, polygonal chains are ascertained in each case for reflections at the object caused by form features. The form features are classified on the basis of the behavior of the polygonal chains over the at least two camera images and a two-dimensional representation is generated, the latter representing a spatial distribution of deformations. Moreover, the invention relates to a corresponding apparatus.