morphologyEx

morphologyEx

cv2.morphologyEx(src, op, kernel[, dst[, anchor[, iterations[, borderType[, borderValue]]]]])

• src: The source image on which the morphological operation is to be performed. This can be a grayscale or binary image.
• op: The type of morphological operation to perform. Possible values are:cv2.MORPH_OPEN: Opening (Erosion followed by Dilation).
  • cv2.MORPH_CLOSE: Closing (Dilation followed by Erosion).
  • cv2.MORPH_GRADIENT: Morphological Gradient (Difference between Dilation and Erosion).
  • cv2.MORPH_TOPHAT: Top Hat (Difference between input image and Opening of the image).
  • cv2.MORPH_BLACKHAT: Black Hat (Difference between the Closing of the image and the input image).

• kernel: Structuring element used for the operation (can be created using cv2.getStructuringElement()).
• dst (optional): Output image of the same size and type as the source image.
• anchor (optional): Anchor point for the kernel. Default is (-1, -1), which means the anchor is at the kernel center.
• iterations (optional): Number of times the operation is applied.
• borderType (optional): Pixel extrapolation method. Default is cv2.BORDER_CONSTANT.
• borderValue (optional): Border value in case of a constant border type. Default is 0.

Morphological gradient

• The morphological gradient is a morphological operation that highlights the edges or boundaries of objects in a binary or grayscale image.
• It is computed as the difference between the dilation and erosion of the image.
• This operation helps in edge detection and can be particularly useful for identifying contours.
• The morphological gradient of image A with Structuring Element B is given as:

• Where dilation expands the boundaries of the objects
• Erosion shrinks the boundaries of the objects

Steps to compute Morphological Gradient

• Perform dilation on the image using the given structuring element.
• Perform erosion on the image using the same structuring element.
• Subtract the eroded image from the dilated image.

Applications:

• The morphological gradient detects edges by calculating the difference between dilation and erosion of an image.
• It’s useful for boundary detection and identifying object outlines.

Top hat

• Morphological top-hat transformation (also called white top-hat) is a morphological operation that highlights small elements or objects that are brighter than their surroundings.
• It is useful for detecting bright objects on a darker background.

The top hat transformation is computed as difference between original image and closing of the image.

Tophat(A) = A – Opening (A,B)

• Where A is the input image
• Opening (A) is the opening of the image

Black hat

• The Black Hat operation is a morphological transformation that highlights the darker regions in an image which are smaller than the structuring element.
• It is the difference between the closing of the image and the original image

The black hat transformation is computed as difference between original image and closing of the image.

blackhat(A) = Closing (A,B) - A

• Where A is the input image
• Closing (A) is the closing of the image

Practice Exercise

Views: 0