Wolff, T., Still, J. D., Parkhurst, D. J. & Dark, V. J. (2007). Invariant Features Detected with Computer Vision Allow Better Human Object Recognition in Photographs [abstract]. Poster presented at the meeting of the Midwestern Psychological Association, Chicago, IL.
Do invariant features contribute to object recognition? Using the Scale Invariant Feature Transform (Lowe, 1999), we created photograph fragments with varying numbers of invariant features. Objects in photographic segments with fewer invariant features were identified less accurately. Therefore, invariant features, as detected by SIFT, are important for human object recognition.