I developed this application on C++
I am using 5X5 and 3X3 kernels to convolve with Image. As I know convolution is computational Intensive and I have to convolve many kernels with my image to achieve the result, the execution takes 2 seconds. I would like to reduce the processing time.

When I sequentially convolve kernel with image, the values difference between two sequentially convolution is very less in many places, because the pattern is not changing much. I would like to know using this idea, can I able to reduce the computational time.

8 Years
Discussion Span
Last Post by Salem

I've not heard of that speedup - you're saying that if one region in the image is the same as next region, there is not need to compute the correlation again? I don't see how the algorithm would have any way of knowing that (besides some operation that would take just as long as the actually correlation).


HI thanks for the reply

can you give any other idea to speed up the convolution



> I would like to reduce the processing time.
To what - video frame rate?

Which OS/Compiler are you using?
Do you have multiple cores on your CPU? Are you using all of them?

This topic has been dead for over six months. Start a new discussion instead.
Have something to contribute to this discussion? Please be thoughtful, detailed and courteous, and be sure to adhere to our posting rules.