Abstract:
In this final year project, we're diving into the exciting world of turning words into
pictures using Generative Adversarial Networks (GANs) and Convolutional Neural
Networks (CNNs). It's like teaching a computer to understand what you're describing
and making a picture out of it - a mix of art and technology that's super fascinating!.
Generative Adversarial Networks (GANs) work like a team of two friends. One friend,
the "generator," tries to make pictures from the words you tell it. The other friend, the
"discriminator," checks if those pictures look real or not. As they practice, the
computer gets really good at creating pictures that match your words. And then there's
Convolutional Neural Networks (CNNs), which are like the computer's eyes - they
help it see shapes and colours in the pictures. We're digging into how GANs and CNNs
team up to make this happen. We're figuring out how the computer learns to change
words into images that make sense. This could be a big help for artists, designers, and
anyone who wants to show their ideas as pictures without drawing or taking photos.
Our project is like showing computers how to become artists, turning words into
pictures in a whole new way. In this project, Exploring all about GANs and CNNs,
and how they work together to create something cool. The process sharing the steps of
how the computer goes from understanding your words to making pictures that match
them. This kind of skill could change the way we make pictures and bring thoughts to
life. Our project is a journey into a world where computers can understand and create
from words - an adventure where technology and creativity meet
