imageBinary: Segmentation and Binarization

In rwang14/implant: A High-throughput Phenotyping Pipeline for Image Processing and Functional Growth Curve Analysis

Description

This function uses the Double-Criterion Thresholding method (DCT) to segment the object of study from the background of an image, and tranform the image to a binary image, i.e., a black and white image.

Usage

imageBinary(image, weight = c(-1, 2, -1), threshold1 = 30 / 255,
threshold2 = 0.075)

Arguments

image	an array of pixels of the image for processing.
weight	a 3 by 1 vector. The three elements indicate the weight of the pixel intensities of R,G,B, respectively. In default, it takes the value of c(-1, 2, -1), which helps to construct a relative green ratio.
threshold1,threshold2	Values between 0 and 1. threshold1 is applied to the sum of the RGB intensities. threshold2 is applied on the contrast intensity by the specified weight in the function.

Details

The plant pixels are classified as the intersection of sum of RGB intensities larger than threshold 1 and green intensities larger than threshold 2.

Value

A matrix of the processed image.

Examples

#read an RGB image
library(png)
image = readPNG(system.file("extdata", "image1.png",
                             package = "implant",
                             mustWork = TRUE))[ , ,c(1:3)]
imageB = imageBinary(image,  weight = c(-1, 2, -1),
threshold1 = 30 / 255, threshold2 = 0.05)

rwang14/implant documentation built on Sept. 6, 2020, 3:21 a.m.