How Can a Neural Network Transform Faces into Alien Art?

In summary, the author suggests using a deep learning neural network to learn how to draw a picture like the one an artist drew of a person's face, but he cautions that it may be difficult to find the necessary training data. He suggests starting with libraries that can recognize facial features, and then moving on to a generative adversarial network if the first attempt does not produce satisfactory results.
  • #1
btb4198
572
10
I have a picture of a guy's face and I had an artist draw him as an alien. How do I make a neural network that would take in the original picture and learn how to draw the picture the that artist make?

I want to make a filter, that if you can enter in any guy's face, and the program would draw is like if it was the artist.
 
Technology news on Phys.org
  • #2
btb4198 said:
I have a picture of a guy's face and I had an artist draw him as an alien. How do I make a neural network that would take in the original picture and learn how to draw the picture the that artist make?

I want to make a filter, that if you can enter in any guy's face, and the program would draw is like if it was the artist.
That's interesting and novel. Deep learning neural networks learn from large numbers of examples. If you have 100,000 example pictures of people plus 100,000 examples of how the corresponding alien pictures would look, then you can use those as training data to train a neural network.

The difficulty is not in the deep learning, but the collections of the training data.
 
  • #3
anorlunda,

I have a lot of pictures of different faces and I am going to have the artist do the same thing to them.
So I am working on building a big database.
but again what kind of neural network should I make? All the videos I have seen on the subject, seem to be about finding an object in an image.

but I am not trying to find something
 
  • #4
http://neuralnetworksanddeeplearning.com/

That link it to a free online book. The book explains in detail how to do what you want. It illustrates using a NIST data base of more than 250,000 images of handwritten letters identified by real people.
btb4198 said:
I have a lot of pictures
I hope you really mean that. A quarter million really is a lot. If you mean a few dozen, it won't work well.
 
  • #5
Question,

How does you think Prequel does it's cartoon me?
Do you think they have a quarter Million of face pictures, because I really did not think it would take that many. That seems excessive.
Right now I have 139 different face Pictures redrawing by the same artist.
 
  • #6
btb4198 said:
Question,

How does you think Prequel does it's cartoon me?
Do you think they have a quarter Million of face pictures, because I really did not think it would take that many. That seems excessive.
Right now I have 139 different face Pictures redrawing by the same artist.
I don't know about Prequel, but it is possible that they did it by some means other than deep learning trained neural networks.
 
  • Like
Likes pbuk
  • #7
There are already libraries that can recognize facial features. (see e.g. DeepFace) I would start there. The first thing to learn in programming is to not reinvent the wheel.
 
  • #8
Generative adversarial network (GAN) is what you're looking for. Or cycle GAN which can be used for unpaired images (e.g. a databased of human pictures and a separate one of aliens).

The topic you can look up is image-to-image translation.
 
Last edited:
  • #9
Here is a video explaining how it works.

 
  • #10
Jarvis323 said:
Here is a video explaining how it works.


Thanks, I am going to watch his videos on this
 

FAQ: How Can a Neural Network Transform Faces into Alien Art?

What is deep learning and how does it differ from other types of neural networks?

Deep learning is a subset of machine learning that uses artificial neural networks to process and analyze large amounts of data. It differs from other types of neural networks in that it has multiple hidden layers, which allows it to learn and make decisions on its own without being explicitly programmed.

How does a deep learning neural network work?

A deep learning neural network works by taking in a large amount of data and using multiple layers of interconnected nodes to process and extract features from the data. These features are then combined to make predictions or decisions based on the input data. The network is trained through a process called backpropagation, where the weights of the connections between nodes are adjusted to minimize the error in its predictions.

What are the applications of deep learning?

Deep learning has a wide range of applications, including image and speech recognition, natural language processing, autonomous vehicles, and robotics. It is also used in industries such as healthcare, finance, and marketing for tasks such as data analysis, predictive modeling, and fraud detection.

What are the advantages of using deep learning over traditional machine learning algorithms?

Deep learning has several advantages over traditional machine learning algorithms, including the ability to handle large and complex datasets, automatic feature extraction, and the ability to learn and improve with more data. It also has the potential to outperform traditional algorithms in terms of accuracy and efficiency.

What are the limitations of deep learning?

One limitation of deep learning is its reliance on large amounts of labeled data for training, which can be time-consuming and costly to obtain. It also requires significant computing power and resources to train and run the models. Additionally, deep learning models can be difficult to interpret and explain, making it challenging to understand how they make decisions.

Similar threads

Normalization condition with a neural network
Replies
3
Views
1K
Thoughts on neural networks "discovering" physical concepts
Replies
1
Views
1K
Python Help solving a geometrical matching issue with Graph Neural Networks
Replies
1
Views
882
Python Understanding Graph Neural Networks (GNNs) Tutorials & Examples
Replies
2
Views
2K
How should a physicist learn Machine Learning?
Replies
5
Views
1K
Can artificial intelligence create music?
Replies
18
Views
3K
How can I implement a multi-task deep learning neural network?
Replies
3
Views
1K
Neural network problems with multi-input dependencies
Replies
1
Views
2K
Where can I find examples of applications for trained ART and SOM networks?
Replies
4
Views
5K
Where Can I Learn About Artificial Neural Networks?
Replies
4
Views
3K

Hot Threads

Recent Insights

Back
Top