binimage: Generate binary ordered dissimilarities matrix for VAT...
In zcebeci/VatAna: Visual Assessment of Clustering Tendency for Finding the Number of Clusters in a Dataset

Description Usage Arguments Details Value Author(s) References See Also Examples

View source: R/binimage.R

This function generates the binary ordered dissimilarity matrix (BDM) for VAT analysis.

1	binimage(img, method="otsu", t=NULL, q=0.10, greylevel=256, disp=FALSE)

`img`	A numeric matrix containing the greyscale ordered dissimilarities.
`method`	A character string describes the name of thresholding method to generate the binary image matrix from the greyscale ordered dissimilarities. The default value is `'otsu'` for the Otsu's thresholding method. The option `'fixed'` is for describing an user-defined value as the threshold. If it is assigned as the thresholding method, the user should define an integer threshold value with the argument `t`, otherwise the arithmetic mean of the matrix is used as the threshold value. The option `'auto'` automatically computes the threshold using the formula: `sqrt(2sigma^2 log(n)/n)`. The option `'median'` uses the middle value of greyscale range as the threshold. The `'quant'` option computes a user-defined quantile of the dissimilarites. If this method is used, the argument `q` should be assigned between 0 and 1. The default value of `q` is 0.10 (
`t`	A numeric threshold value for converting the ordered dissimilarities to a binary image matrix. It is used if the method argument is set to `fixed`. The default value is the arithmetic mean of the matrix `img`.
`q`	A numeric quantile value when the method argument is set to `quant`. The default `q` value is 0.10.
`greylevel`	An integer describing the grey levels in the greyscale image. The default value is 256.
`disp`	A logical value whether the the ordered dissimilarities image will be displayed or not. The default value is `TRUE`.

Since this function uses the grey-level dissimilarities matrix as the input, the greyscale image should be generated using the function greyimage at first.

`binimg`	Binary ordered dissimilarities matrix
`threshold`	Threshold value computed to generate the binary matrix

Zeynel Cebeci

Cebeci, Z. & Yildiz, F. (2015). Gorsel Kumelenme Egilimi Degerlendirmesi ve R'de Uygulamasi. Cukurova Universitesi Ziraat Fakultesi Dergisi, 30 (2), 1-8. (URL: https://dergipark.org.tr/en/download/article-file/219860)

findk, findk2, genbinimg, greyimage, vatimage, vatdisp

# Load the dataset iris and use the first four feature columns 
data(protcarbo)
# Run vatimage to build ordered dissimilarities matrix 
vatmat <- vatimage(protcarbo, disp=FALSE)$odm
# Generate grey-level image matrix
greymat <- greyimage(vatmat, greylevel=256, disp=FALSE)
# Generate binary image matrix with automatic thresholding method
binmat <- binimage(vatmat, method="auto", greylevel=256, disp=TRUE)
# Generate binary image matrix with fixed thresholding method
binmat <- binimage(vatmat, method="fixed", t=50, greylevel=256, disp=TRUE)