Convolutional neural network - How to get the feature maps?

Question

I read a few books and articles about Convolutional neural network, it seems I understand the concept but I don't know how to put it up like in the image below:

(source: what-when-how.com)

from 28x28 normalized pixel INPUT, we get 4 feature maps of size 24x24. but how to get them? resizing the INPUT image ? or performing image transformations? but what kind of transformations? or cutting the input image into 4 pieces of size 24x24 by 4 corners? I don't understand the process, to me, it seems they cut up or resize the image to smaller images at each step. please help thanks.

Answer 1

The feature map on CNN is the output of one filter applied to the previous layer. A filter that is given is drawn across the entire previous layer, moved one pixel at a time. Each position results in activation of the neuron and the output are collected in the feature map. You can observe that if the receptive field is moved one pixel from activation to activation, then the field will overlap with the previous activation by (field width - 1) input values.

For instance, In a 32 × 32 image, dragging the 5 × 5 receptive fields across the input image data with a stripe width of 1 will result in a feature map of 28 × 28 (32–5+1 × 32–5+1) output values or 784 distinct activations per image.

You can visualize the filters and the feature maps in Convolutional Neural Network by referring the  following link: https://machinelearningmastery.com/how-to-visualize-filters-and-feature-maps-in-convolutional-neural-networks/