The Second Part of the Trilogy on Autoencoders – Morphing and Finding Similar Images
This time, we aim to find the most similar image in the dataset. Simply encode a face into a matrix of a few numbers. Then, you look at which matrix of encoded numbers…
This time, we aim to find the most similar image in the dataset. Simply encode a face into a matrix of a few numbers. Then, you look at which matrix of encoded numbers resembles the previous matrix the most. Based on this principle, one could create an application to determine which celebrity you resemble the most.
Or do you prefer morphing? You encode two images and then gradually change individual values step by step. The result is decoded once again.
You could also combine these applications. Find someone attractive whom you resemble and morph yourself a bit towards them. 
🙂
Původní zdroj: wordpress
Související články
January 2018
The Conclusion of the Trilogy on Autoencoders or Genesis 2.0 – Right up to the Creation of the First Humans
ReadJanuary 2018
The First Part of the Trilogy on the Use of Autoencoders – Noise Reduction
ReadJanuary 2018