Cite as:
Kim J, 2011, "Visual feature analysis for connoisseurship" Perception 40 ECVP Abstract Supplement, page 219
Visual feature analysis for connoisseurship
J Kim
With the archived artworks of representative Korean modern painters, each painter’s distinctive style was quantitatively extracted with respect to appropriate visual features articulated in paintings. The quantitatively defined artists’ signatures were then applied to authentication of questionable artworks. The shape of face and eye and line features of brushstrokes in paintings, for example, were exploited for the analysis. Faces and lines are special for the human visual system and they have been in the forefront of art as well. It is thus natural to apply the characteristics of human visual information processing to the analysis of works of art. A biologically inspired quantitative analysis of face is based on the harmonics of radial frequency (RF). Considerable evidence has been accumulating that the human visual system has special sensitivity for the RF patterns. The RF analysis decomposing shapes into a series of additive, orthogonal harmonics and the harmonic distance coefficients were used in order to assess similarities and differences between the authentic and the questionable artworks. For the analysis of brushstrokes, Gabor wavelet energy was utilized. The results verified that a scientific approach based on the characteristics of human visual information processing could be usefully applied to connoisseurship.
[Supported by CRCP funded by MoEST (2010K001130)]
These web-based abstracts are provided for ease of seaching and access, but certain aspects (such as as mathematics) may not appear in their optimum form. For the final published version of this abstract, please see
ECVP 2011 Abstract Supplement (complete) size: 2206 Kb
[Publisher's note: The abstracts in this year's ECVP supplement have been published with virtually no copy editing by Pion, thus the standards of grammar and style may not match those of regular Perception articles.]
