Filtering
Convolution with kernels and padding, blurring and noise removal with mean, Gaussian and median filters, and edge detection with Sobel gradients.
About 5 hours of study
Learning objectives
- Apply kernels with valid and same-size output
- Remove noise with the right filter
- Find edges from gradient magnitude and direction
Lessons
- 1
Convolution and kernels Intermediate
Slide a small grid of weights over an image and add up the products: that one operation blurs, sharpens and finds edges. Learn kernels, output sizes, borders and padding, and the difference between correlation and true convolution.
- 2
Blurring and noise removal Intermediate
Real images are noisy. Compare the mean, Gaussian and median filters, see why the median removes salt-and-pepper noise without smearing it, and build a separable Gaussian blur from its formula.
- 3
Edges with Sobel gradients Intermediate
Edges are where brightness changes quickly. Measure that change with the Sobel kernels, combine it into a gradient magnitude and direction, and thin thick edges the way the Canny detector does.
Module practice
- Computer vision: Slide a kernel over an imageEasy
- Computer vision: Pad an image three waysMedium
- Computer vision: Same-size true convolutionHard
- Computer vision: A 3 x 3 mean filterEasy
- Computer vision: Median filter with replicated bordersMedium
- Computer vision: A separable Gaussian blurHard
- Computer vision: Sobel gradientsEasy
- Computer vision: An edge map from gradient magnitudeMedium
- Computer vision: Thin edges with non-maximum suppressionHard