How to decide which Filter or Kernel Matrix is to be applied to the image for different convolution operations for different feature extractions ? Like for eg in case of blurring of image, we gave average filter - np.ones((3, 3))/9 and for edge detection we gave - np.array([[1,0,-1] , [1,0,-1] , [1,0,-1]])
CNN - Implementing Covolutions, Understanding Filters
hey @gautam75 ,
understanding these things is basically depended upon experiments.
You can experiment as much as as you and based on results you can get these values.
Currently the one , that you just shared are also a result of someone’s experiment.
So, there is hard course rule that these values will work everytime, most of the times they will work , but they too might lack sometime
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.