Class ThresholdBlock<T extends ImageGray<T>,​S extends ImageBase<S>>

All Implemented Interfaces:
Direct Known Subclasses:

public class ThresholdBlock<T extends ImageGray<T>,​S extends ImageBase<S>>
extends Object
implements InputToBinary<T>

Computes image statistics in regularly spaced blocks across the image. Then computes an average of the statistics in a block within a local 3x3 grid region. The average statistics in a local 3x3 grid region is used to reduce the adverse affects of using a grid. Ideally a local region around each pixel would be used, but this is expensive to compute. Since a grid is used instead of a pixel local region boundary conditions can be an issue. For example, consider a black square in the image, if the grid just happens to lie on this black square perfectly then if you look at only a single grid element it will be considered textureless and the edge lost. This problem isn't an issue if you consder a local 3x3 region of blocks.

The size each block in the grid in pixels is adjusted depending on image size. This is done to minimize "squares" in the upper image boundaries from having many more pixels than other blocks.

The block based approach used here was inspired by a high level description found in AprilTags.

  • Field Details

  • Constructor Details

    • ThresholdBlock

      public ThresholdBlock​(ThresholdBlock.BlockProcessor<T,​S> processor, ConfigLength requestedBlockWidth, boolean thresholdFromLocalBlocks, Class<T> imageClass)
      Configures the detector
      requestedBlockWidth - About how wide and tall you wish a block to be in pixels.
  • Method Details

    • process

      public void process​(T input, GrayU8 output)
      Converts the gray scale input image into a binary image
      Specified by:
      process in interface InputToBinary<T extends ImageGray<T>>
      input - Input image
      output - Output binary image
    • applyThreshold

      protected void applyThreshold​(T input, GrayU8 output)
      Applies the dynamically computed threshold to each pixel in the image, one block at a time
    • computeStatistics

      protected void computeStatistics​(T input, int innerWidth, int innerHeight)
      Computes the min-max value for each block in the image
    • isThresholdFromLocalBlocks

      public boolean isThresholdFromLocalBlocks()
    • setThresholdFromLocalBlocks

      public void setThresholdFromLocalBlocks​(boolean thresholdFromLocalBlocks)
    • getInputType

      public ImageType<T> getInputType()
      Specified by:
      getInputType in interface InputToBinary<T extends ImageGray<T>>