Class ComputeLocalSauvolaThreshold<T extends RealType<T>>

  • All Implemented Interfaces:
    Computers.Arity4<Iterable<T>,​T,​Double,​Double,​BitType>, Consumers.Arity5<Iterable<T>,​T,​Double,​Double,​BitType>

    public class ComputeLocalSauvolaThreshold<T extends RealType<T>>
    extends Object
    implements Computers.Arity4<Iterable<T>,​T,​Double,​Double,​BitType>

    This is a modification of Niblack's thresholding method. In contrast to the recommendation on parameters in the publication, this implementation operates on normalized images (to the [0, 1] range). Hence, the r parameter defaults to half the possible standard deviation in a normalized image, namely 0.5.

    Sauvola J. and Pietaksinen M. (2000) "Adaptive Document Image Binarization" Pattern Recognition, 33(2): 225-236. PDF

    Original ImageJ implementation by Gabriel Landini.

    Author:
    Stefan Helfrich (University of Konstanz)
    Implementation Note:
    op names='threshold.localSauvola', priority='-100.'