(Scroll down to see more Pikazo images)
On December 11, 2015, I read a TechCrunch article titled ‘How Pikazo Turns Your Photos Into Magic‘. The article was just what I was looking for and didn’t even know it.
I’ve always had an eye for visual/creative things but have never pursued digging very deep into learning how to actually create anything of interest. I’ve made beaded jewelry with friends but haven’t been patient enough to make complicated pieces. The fun was simply doing something crafty with friends. I enjoy taking photographs and found myself filling up my Facebook and Instagram pages with photos. So when I saw the article about turning photos into magic, I kept reading….
This sentence in the TechCrunch article caught my attention: “The latest photo app to grab the world by the eyeballs is called Pikazo. Created by a programmer and an artist, the app “simulates a visual cortex” and takes 10 minutes to change a normal picture into something out of the Tate Modern.” The TechCrunch article goes on to say that “The creators Karl Stiefvater and Noah Rosenberg have worked together for years. They came up with Pikazo over beers when Karl talked about Google’s Deep Dream Generator and said they could use it to make amazing images. Rosenberg, a designer, was hooked.”
That sounded cool. I installed the app and started playing. Holy moly — I quickly found that the images I ‘created’ in the Pikazo app were super cool and did look like pieces of art, and notably art that only takes 10 minutes to make. I quickly became obsessed – a super-user 🙂 I started by using the styles that Pikazo provides and soon realized that I could add my own ‘style’ to my images. I began searching Google images for all sorts of artwork and designs…anything that seemed like it would be a cool style for one of my photos.
I wanted to understand a little more about what was happening on the back end so I learned about the Deep Dream Generator. I found out that “Google has spent the last few years teaching computers how to see, understand, and appreciate our world. It’s an important goal that the search giant hopes will allow programs to classify images just by “looking” at them. And this is where Google’s deep dream ideas originate. With simple words you give to an AI program a couple of images and let it know what those images contain ( what objects – dogs, cats, mountains, bicycles, … ) and give it a random image and ask it what objects it can find in this image. Then the program start transforming the image till it can find something similar to what it already knows and thus you see strange artifacts morphing in the dreamed image (like eyes or human faces morphing in image of a pyramid ).”
Wowza. Artificial intelligence. Artificial neural networks (ANN). Is this a replica of what our brain sees? A computer brain that ‘sees’ things similarly to what our real brain sees? This is what is going on with artificial neural networks: “We train an artificial neural network by showing it millions of training examples and gradually adjusting the network parameters until it gives the classifications we want. The network typically consists of 10-30 stacked layers of artificial neurons. Each image is fed into the input layer, which then talks to the next layer, until eventually the “output” layer is reached. The network’s “answer” comes from this final output layer.“
I could go on and on but you’ve got to just play around with it and see it for yourself. Here is a sampling of what I have done with Pikazo so far……