Compute Image Gradient Intensity - No Noise

[robi10101298]

Hello guys, if I have an image with 11x11 pixels and in the center of the image is a square of 5x5 pixels, with the gray level of the background 0 and the gray level of the square is 50. How can I compute the result of the magnitude of edges(intensity of the contour) or better said the gradient of the contour given by the compass operator for this image taking into account that the image is not noisy? I need to apply simple derivation because the image it's not noisy.

 

[jvicens]

Hi there,

To compute the magnitude of edges or the gradient of the contour for this image using the compass operator, you can use the following steps:

1. First, convert the image to grayscale if it is not already in grayscale.

2. Next, apply a Gaussian filter to smooth out any noise in the image. This will help to reduce any false edges that may be caused by noise.

3. Then, use the compass operator on the smoothed image to detect the edges. The compass operator is a type of edge detection algorithm that uses a set of predefined kernels to detect edges in multiple directions.

4. Once you have the edge detection results, you can compute the magnitude of the edges by taking the square root of the sum of squares of the horizontal and vertical edge values at each pixel.

5. Finally, you can visualize the gradient of the contour by plotting the magnitude values on a gradient map, where the higher values correspond to stronger edges.

Since the image is not noisy, you can use a simple derivation method to compute the gradient of the contour. However, if the image was noisy, you may need to use a more robust method such as the Canny edge detector.

I hope this helps! Let me know if you have any further questions.