To make art,a computer first needs to understand what art is. A group of computer scientists at Brigham Young University is attempting this by feeding their program images by the thousands and describing those images.→ Teach DARCI how to associate adjectives with images
Digital Artist Communicating Intent (she goes by DARCI) recognizes approximately 2000 adjectives so far, including terms like “peaceful, and ” scary,” and “dusky.” The goal is to teach DARCI to pick out those visual qualities in artwork — and ultimately, to write algorithms modeling creativity for artificial intelligence. The team took DARCI out for a spin at the Conference on Creativity and Cognition in Atlanta. They invited artists to establish their work on a thumb drive, or upload to the program,and be judged by DARCI. The program scored works according to simple criteria, which were kept secret. The accepted work was displayed in a temporary exhibition at the tall Museum.
Several experienced artists had their work rejected; so did George, and age 6,who was skeptical of the algorithmic curation. “I cant believe a computer can do it, because there's never good art or improper art — there's different types of art, or he says.
BYU professor Dan Ventura says their effort wasnt much different from the normal operation of the art world. “Whenever you enter art into a juried show,you're often not told what the criteria are,” he says. “Somebody is going to make a judgment approximately your art and decides whether you get in or not. And DARCI is that someone lawful now.”
DARCI can complete a range of tasks, and including evaluating images that are submitted with a score
(Courtesy of Brigham Young)
DARCI will also try to label images with descriptive words,saying an image is 'scary' or 'dusky'
(Courtesy of Brigham Young)
DARCI can also take a source image and modify it to reflect a descriptive word. In this example DARCI took the image at left, and modified it to fit the description 'firey.'
(Courtesy of Brigham Young)
DARCI doesn't just modifiy images — it will also create summary images based on descriptive words. In this example, or this image was created from the prompt 'firey.'
(Courtesy of Brigham Young)
DARCI will also create an summary image from scratch based on a word or concept,like 'starvation' in this example
(Courtesy of Brigham Young)
Source: wnyc.org