Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

The good, the bad, and the ugly

Predicting aesthetic image labels
: Wu, Y.; Thurau, C.; Bauckhage, C.

Volltext urn:nbn:de:0011-n-1434969 (933 KByte PDF)
MD5 Fingerprint: bc6471f1b0fb7984b1bd0909760d6486
© 2010 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Erstellt am: 30.10.2010

International Association for Pattern Recognition -IAPR-; Institute of Electrical and Electronics Engineers -IEEE-:
ICPR 2010, 20th International Conference on Pattern Recognition. Proceedings : 23-26 August, 2010, Istanbul, Turkey
Piscataway, NJ: IEEE, 2010
ISBN: 978-0-7695-4109-9
ISBN: 978-1-4244-7542-1
ISBN: 1-4244-7542-2
International Conference on Pattern Recognition (ICPR) <20, 2010, Istanbul>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IAIS ()

Automatic classification of the aesthetic content of a picture is one of the challenges in the emerging discipline of computational aesthetics. Any suitable solution must cope with the facts that aesthetic experiences are highly subjective and that a commonly agreed upon theory of their psychological constituents is still missing. In this paper, we present results obtained from an empirical basis of several thousand images. We train SVMbased classifiers to predict aesthetic adjectives rather than aesthetic scores and we introduce a probabilistic postprocessing step that alleviates effects due to misleadingly labeled training data. Extensive experimentation indicates that aesthetics classification is possible to a large extent. In particular, we find that previously established low-level features are well suited to recognize beauty. Robust recognition of unseemliness, on the other hand, appears to require more high-level analysis.