DSP Tool
The DSP tool we are using in our project from class is a Gaussian blur. Gaussian blur refers to the blurring of an image and making it smooth. It is commonly used to reduce image noise and detail.
The reason we are using Gaussian blur to help with the detection of melanoma is because it helps remove the sharpness of the potential infection which will make it easier to use edge and blob detection.
Example of Gaussian Blur
Image Courtesy of: and https://en.wikipedia.org/wiki/Gaussian_blur
Mathematically, a Gaussian blur filter is a low pass filter that convolves adjacent pixels with the Gaussian function (shown to the right) to smooth out the image and reduce high frequency noise.
Image Courtesy of: and https://en.wikipedia.org/wiki/Gaussian_blur
-
x is the horizontal distance from the origin
-
y is the vertical distance from the origin
-
σ is your prefered standard deviation for the Gaussian (normal) distribution
Example of Gaussian blur matrix with a standard deviation of 0.84
Image Courtesy of: and https://en.wikipedia.org/wiki/Gaussian_blur