πCommon Concepts
π Important Terms
Term | Description |
Convolution | Applying some filter on an image so certain features in the image get emphasized |
π Convolution Example
π€ How did we find -7?
We did element wise product then we get the sum of the result matrix; so:
And so on for other elements π
πΌ Visualization of Calculation
π Edge Detection
An application of convolution operation
π Edge Detection Examples
Result: horizontal lines pop out
Result: vertical lines pop out
π What About The Other Numbers
There are a lot of ways we can put number inside elements of the filter.
For example Sobel filter is like:
Scharr filter is like:
Prewitt filter is like:
So the point here is to pay attention to the middle row
And Roberts filter is like:
β¨ Another Approach
We can tune these numbers by ML approach; we can say that the filter is a group of weights that:
By that we can get -learned- horizontal, vertical, angled, or any edge type automatically rather than getting them by hand.
π€ΈββοΈ Computational Details
If we have an n*n
image and we convolve it by f*f
filter the the output image will be n-f+1*n-f+1
π Downsides
π If we apply many filters then our image shrinks.
π€¨ Pixels at corners aren't being touched enough, so we are throwing away a lot of information from the edges of the image .
π‘ Solution
We can pad the image πͺ
π§ References
Last updated