chore: Started to describe some more commands

docs/fundamentals/commands/command_blur.md

@@ -0,0 +1,31 @@
+
+(command-blur)=
+# Blur
+
+:::{sidebar} Filter kernel
+
+In image processing, a kernel, convolution matrix, or mask is a small matrix used for blurring, sharpening, embossing, edge detection, and more. 
+This is accomplished by doing a convolution between the kernel and an image. 
+Or more simply, when each pixel in the output image is a function of the nearby pixels (including itself) in the input image, the kernel is that function.
+
+
+
+```{figure} images/blur_kernerl.drawio.svg
+:class: full-image
+```
+
+https://en.wikipedia.org/wiki/Kernel_(image_processing)
+:::
+
+Blur algorithms are used to reduce image noise and details.
+
+ImageC provides two different blur algorithms, "normal" blur and Gaussian blur.
+For both the filter kernel size can be set.
+The larger the kernel, the more details are removed from the image.
+
+Gaussian blur uses a Gaussian function to blur the image.
+Compared to the normal blur gaussian blur tends to preserve edges slightly better and avoids sharp transitions between blurred regions.
+
+:::{hint}
+Bigger filter kernels removes more noise and details from the image. Use gaussian blur to preserve edges in a better way than normal blur.
+:::

docs/fundamentals/commands/command_rolling_ball.md

@@ -0,0 +1,37 @@
+
+(command-rolling-ball)=
+# Rolling ball
+
+:::{sidebar} Thresholding
+
+
+The rolling-ball algorithm was inspired by Stanley Sternberg’s article, “Biomedical Image Processing”, IEEE Computer, January 1983.
+
+```{figure} images/rolling_ball_reseacrh_gate.jpeg
+:class: full-image
+```
+
+:::
+
+
+The rolling ball algorithm is a background subtraction algorithm, with the goal to remove most of the background noise.
+
+This is achieved by creating a local background around a virtual ball.
+Within the radius of the ball, the average intensity is calculated.
+This is done for the entire image.
+The result is subtracted from the original image.  
+
+This port from ImageJ contains two ball types, a spheral ball and a paraboloid.
+A paraboloid handles edges more gently, reducing the appearance of artifacts along boundaries. 
+This is beneficial in applications such as microscopy, where accurate boundary representation is essential.
+
+:::{hint}
+The radius of the ball should be set to at least the size of the largest object that does not belong to the background.
+:::
+
+:::{note}
+The implementation in ImageC was taken from the original ImageJ and ported to C++ based on the NIH Image Pascal version by Michael Castle and Janice Keller of the University of Michigan Mental Health Research Institute.
+:::
+
+
+