Canny Edge Detection is used to detect the edges in an image. It accepts a gray scale image as input and it uses a multistage algorithm.

You can perform this operation on an image using the Canny() method of the imgproc class, following is the syntax of this method.

Canny(image, edges, threshold1, threshold2)

This method accepts the following parameters −

• image − A Mat object representing the source (input image) for this operation.

• edges − A Mat object representing the destination (edges) for this operation.

• threshold1 − A variable of the type double representing the first threshold for the hysteresis procedure.

• threshold2 − A variable of the type double representing the second threshold for the hysteresis procedure.

Example

Following program is an example demonstrating, how to perform Canny Edge Detection operation on a given image.

import org.opencv.core.Core;
import org.opencv.core.Mat;

import org.opencv.imgcodecs.Imgcodecs;
import org.opencv.imgproc.Imgproc;

public class CannyEdgeDetection {
   public static void main(String args[]) throws Exception {
      // Loading the OpenCV core library
      System.loadLibrary(Core.NATIVE_LIBRARY_NAME);

      // Reading the Image from the file and storing it in to a Matrix object
      String file = "E:/OpenCV/chap17/canny_input.jpg";

      // Reading the image
      Mat src = Imgcodecs.imread(file);

      // Creating an empty matrix to store the result
      Mat gray = new Mat();

      // Converting the image from color to Gray
      Imgproc.cvtColor(src, gray, Imgproc.COLOR_BGR2GRAY);
      Mat edges = new Mat();

      // Detecting the edges
      Imgproc.Canny(gray, edges, 60, 60*3);

      // Writing the image
      Imgcodecs.imwrite("E:/OpenCV/chap17/canny_output.jpg", edges);
      System.out.println("Image Loaded");
   } 
}

Assume that following is the input image canny_input.jpg specified in the above program.

Output

On executing the above program, you will get the following output −

Image Processed

If you open the specified path, you can observe the output image as follows −