src: https://developersbreach.com/convolution-neural-network-deep-learning/

Computer Vision: CNNs for Images. Why?

Start with this article, if you need a refresher oN CNNs:

Computer Vision: Convolutional Neural Networks (CNNs)

Convolutional layers are preferred over fully connected layers for processing images in neural networks due to their ability to capture local spatial patterns and reduce the number of parameters. Here’s why:

1. Local Connectivity: Images have a spatial structure, meaning that nearby pixels are often related to each other. Convolutional layers exploit this property by using small filters that slide across the image to capture local patterns. This local connectivity allows the network to learn features like edges, textures, and simple shapes, which are building blocks for more complex features.
2. Parameter Sharing: In convolutional layers, the same set of weights (filter) is applied at different spatial locations of the input. This sharing of parameters reduces the total number of parameters compared to fully connected layers, which have connections between every input and output neuron. This parameter sharing helps prevent overfitting, as it enforces some degree of translation invariance.