Erratum to: J Math Imaging Vis (2013) 47:79–92 DOI 10.1007/s10851-012-0356-9

The following passages were not properly cited in the original paper. The authors apologize for this error and would like to update the paper accordingly.

On page 2, lines 174–176 should read as: “The original LBP operator [23] creates labels for the image pixels by thresholding their 3×3 neighborhood with the center value” [36].

And lines 187–198 should read as: As pointed out in [35]: “another extension to the original operator is the definition of the so called uniform patterns, which can be used to reduce the length of the feature vector and implement a simple rotation-invariant descriptor. This extension was inspired by the fact that some binary patterns occur more commonly in texture images than others. A local binary pattern is called uniform if it contains at most two transitions from 0 to 1 or vice versa when it is traversed circularly. Ojala et al. [24] noticed in their experiments that uniform patterns account for a little less than 90 % of all patterns when using a (8, 1) neighborhood and for around 70 % with a (16, 2) neighborhood.”

  1. [35]

    Pietikäinen, M.: Local Binary Patterns, Scholarpedia 5(3), 9775 (2010).

  2. [36]

    Hadid, A., Zhao, G., Ahonen, T., Pietikäinen, M.: Face analysis using local binary patterns. In: Handbook of Texture Analysis, pp. 347–373 (2007).