Expansion and corrosion
In fact, if you do not know about expansion and corrosion, you need to read this article first to understand image processing, corrosion, expansion and refinement
Expansion and corrosion are the basis of morphological processing and many morphological algorithms are based on these two operations.
(1) inflation
Is based on taking the image of B relative to its own origin and shifting the image by Z. A expanded by B is the set of all the displacements Z, such that there is at least one element of overlap with A. We can rewrite the above equation as:
Structural element B can be regarded as a convolution template. The difference is that inflation is based on set operation and convolution is based on arithmetic operation, but the processing process of the two is similar.
⑴ Scan every pixel of image A with structural element B
(2) Make “and” operation with the structure element and its covered binary image
⑶ If both are 0, the pixel in the resulting image is 0. Otherwise, it is 1
(2) corrosion
For sets A and B in Z,B corrodes A as follows:
⑴ Scan every pixel of image A with structural element B
(2) Make “and” operation with the structure element and its covered binary image
⑶ If both are 1, the pixel in the resulting image is 1. Otherwise, it is 0
The result of etching is to reduce the original binary image by one turn.
⑷ Hit (match) or miss transform
Their applications are extensive:
Eliminate noise
They isolate independent image elements and join adjacent elements.
The Description of the OpenCV functions is erode and dilate
erode
Erode (InputArray SRC,// Original image
OutputArray DST,// Output image // etch operation of the kernel. If not specified, the default is a simple 3×3 matrix. Otherwise, we need to specify its shape explicitly, using getStructuringElement:
InputArray kernel,
Point anchor = Point(-1,-1),
int iterations =1,
int borderType = BORDER_CONSTANT,
const Scalar& borderValue = morphologyDefaultBorderValue()
)
Dilate (use of parameters as above)
dilate(InputArray src,
OutputArray dst,
InputArray kernel,
Point anchor = Point(-1,-1),
int iterations =1,
int borderType = BORDER_CONSTANT,
const Scalar& borderValue = morphologyDefaultBorderValue()
)
getStructuringElemen
// where shap is the kernel shape, ksize is the kernel size, and anchor is the anchor position
Mat getStructuringElement(
int shape,
Size ksize,
Point anchor= Point(-1,-1)
)
Shap comes in three shapes
Rectangle: MORPH_RECT
X-type: MORPH_CROSS
The oval: MORPH_ELLIPSE
Code implementation
corrosion
– (void)eroding
{
int erosion_type;
/// dilation_elem global variable int, used to control the selected kernel shape
if(dilation_elem == 0) {
erosion_type = MORPH_RECT; / / rectangle
} else if(dilation_elem == 1) {
erosion_type = MORPH_CROSS; / / cross
} else {
erosion_type = MORPH_ELLIPSE; / / round
}
/// specify the kernel erosion_size global variable. I’m using slider. value to control erosion_size
Mat element = getStructuringElement(erosion_type, CV: : Size (2 * * erosion_size erosion_size + 1, 2 + 1), CV: : Point (erosion_size erosion_size));
// Corrosion operation
erode(src, dst, element);
self.secondImageView.image = MatToUIImage(dst);
}
Effect drawing (one of them)
inflation
– (void)diating
{
int erosion_type;
/// dilation_elem global variable int, used to control the selected kernel shape
if(dilation_elem == 0) {
erosion_type = MORPH_RECT; / / rectangle
} else if(dilation_elem == 1) {
erosion_type = MORPH_CROSS; / / cross
} else {
erosion_type = MORPH_ELLIPSE; / / round
}
/// specify the kernel erosion_size global variable. I’m using slider. value to control erosion_size
Mat element = getStructuringElement(erosion_type, CV: : Size (2 * * erosion_size erosion_size + 1, 2 + 1), CV: : Point (erosion_size erosion_size));
// Expand operation
dilate(src, dst, element);
self.secondImageView.image = MatToUIImage(dst);
}
Effects (one of them)
The resources
6. stranded and Dilating
6. Eroding and Dilating
Image processing corrosion expansion refinement