Image Thresholding Based on Otsu’s Method using OpenCV

Image thresholding is a technique that allows to perform image binarization based on pixel values. Usually, if the pixel value is greater than a threshold, it is set to a maximum value (often 255 – white), otherwise it is set to 0 (black). There are various methods to calculate threshold value. One of them is Otsu’s method. It is a global thresholding algorithm, where a single threshold value is applied for the whole image.

OpenCV offers threshold function to perform image thresholding. We can specify THRESH_OTSU flag as argument to apply Otsu’s method to calculate threshold value.

import cv2

img = cv2.imread('test.jpg')
grayImg = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
thresh, binaryImg = cv2.threshold(grayImg, 0, 255, cv2.THRESH_OTSU)


cv2.imshow('RGB image', img)
cv2.imshow('Binary image', binaryImg)
#include <iostream>
#include <opencv2/opencv.hpp>

using namespace cv;

int main()
    Mat img = imread("test.jpg");
    Mat grayImg;
    cvtColor(img, grayImg, COLOR_BGR2GRAY);
    Mat binaryImg;
    double thresh = threshold(grayImg, binaryImg, 0, 255, THRESH_OTSU);

    std::cout << thresh << std::endl;

    imshow("RGB image", img);
    imshow("Binary image", binaryImg);

    return 0;
package app;

import org.opencv.core.Core;
import org.opencv.core.Mat;
import org.opencv.highgui.HighGui;
import org.opencv.imgcodecs.Imgcodecs;
import org.opencv.imgproc.Imgproc;

public class Main
    static { System.loadLibrary(Core.NATIVE_LIBRARY_NAME); }

    public static void main(String[] args)
        Mat img = Imgcodecs.imread("test.jpg");
        Mat grayImg = new Mat();
        Imgproc.cvtColor(img, grayImg, Imgproc.COLOR_BGR2GRAY);
        Mat binaryImg = new Mat();
        double thresh = Imgproc.threshold(grayImg, binaryImg, 0, 255, Imgproc.THRESH_OTSU);


        HighGui.imshow("RGB image", img);
        HighGui.imshow("Binary image", binaryImg);


Calculated threshold value (T) is 155. Result:

Grayscale image converted to binary image using Otsu's method and OpenCV

Leave a Comment

Your email address will not be published. Required fields are marked *