Rotational invariance is a model's ability to produce the same or correct classification despite changes in an object's orientation. In image recognition, a rotationally invariant system can identify an object even when it appears rotated.
In an image classification problem, an algorithm's ability to successfully classify images even when the orientation of the image changes. For example, the algorithm can still identify a tennis racket whether it is pointing up, sideways, or down. Note that rotational invariance is not always desirable; for example, an upside-down 9 shouldn't be classified as a 9. See also translational invariance and size invariance.