AForge.NET

  :: AForge.NET Framework :: Articles :: Forums ::

Convolution filter returns image with same size as input

The forum is to discuss topics from different artificial intelligence areas, like neural networks, genetic algorithms, machine learning, etc.

Convolution filter returns image with same size as input

Postby Nerfling » Wed Jul 20, 2016 6:53 am

Hello,

First of all, I'm not very familiar with convolutional neural networks yet.

I tried to apply a convolution filter in this way:

Code: Select all
Convolution _convolution_filter = new Convolution(_kernel_weights); //3x3 random weight kernel
Bitmap _result = _convolution_filter.Apply(_input_bitmap);


It seems that it works but the filter returns a bitmap with the same dimensions as the input bitmap.

I've heard that through convolution the image should get smaller by a few pixels each time the filter is applied but this doesn't seem the case.

Am I doing something wrong?

Any help and advice is appreciated,
Nerfling.
Nerfling
 
Posts: 1
Joined: Wed Jul 20, 2016 6:42 am

Re: Convolution filter returns image with same size as input

Postby andrew.kirillov » Wed Jul 20, 2016 8:20 am

Hello,

Nerfling wrote:First of all, I'm not very familiar with convolutional neural networks yet.

What you are doing (and asking about) has zero relation to neural networks.

Nerfling wrote:I've heard that through convolution the image should get smaller by a few pixels each time the filter is applied but this doesn't seem the case.

It really depends on implementation. Images do not have to get smaller in size.
With best regards,
Andrew


Interested in supporting AForge.NET Framework?
User avatar
andrew.kirillov
Site Admin, AForge.NET Developer
 
Posts: 3429
Joined: Fri Jan 23, 2009 9:12 am
Location: UK




Return to Artificial Intelligence