I don't know if it's art, but I know what I like
Scientists have developed a mathematical program that enables a computer to 'appreciate' works of art.
Devised by a team from the Department of Computer Sciences at the University of Haifa, the technology allows the computer to 'know' whether a piece of artwork is the work of Leonardo da Vinci, for example, or a less well-known artist.
"The field of computer vision is very complex and multifaceted. We hope that our new development is another step forward in this field," said professor Daniel Keren who developed the program.
The researchers first 'taught' the computer to identify the works of different artists by turning the drawings of nature, people, flowers and other scenes into a series of mathematical symbols, sines and cosines.
After the computer 'learned' some of the works of each artist, it was able to master the individual style of each artist and identify that artist when looking at other works which the computer had never seen.
Professor Keren said that the program can identify the works of a specific artist even if they depict different scenes.
"As soon as the computer learns to recognise the clock drawings of Dali, it will recognise his other paintings even without clocks," he said.
"As soon as the computer learns to recognise the swirls of Van Gogh, it will recognise them in pictures it has never seen before."
This new development is a step forward in the field of computer vision, according to the scientists.
"Human vision has undergone millions of years of evolution and our field is only 30 years old," explained Professor Keren.
"At this stage computers still have difficulty doing things that are very simple for people, for example, recognising a picture of a human face.
"A computer has difficulty identifying when a picture is of a human face or how many faces are in a picture. However, computers are very good at simulating and sketching 3D images like the arteries in the brain or a road network."
Scientists have developed a mathematical program that enables a computer to 'appreciate' works of art.
Devised by a team from the Department of Computer Sciences at the University of Haifa, the technology allows the computer to 'know' whether a piece of artwork is the work of Leonardo da Vinci, for example, or a less well-known artist.
"The field of computer vision is very complex and multifaceted. We hope that our new development is another step forward in this field," said professor Daniel Keren who developed the program.
The researchers first 'taught' the computer to identify the works of different artists by turning the drawings of nature, people, flowers and other scenes into a series of mathematical symbols, sines and cosines.
After the computer 'learned' some of the works of each artist, it was able to master the individual style of each artist and identify that artist when looking at other works which the computer had never seen.
Professor Keren said that the program can identify the works of a specific artist even if they depict different scenes.
"As soon as the computer learns to recognise the clock drawings of Dali, it will recognise his other paintings even without clocks," he said.
"As soon as the computer learns to recognise the swirls of Van Gogh, it will recognise them in pictures it has never seen before."
This new development is a step forward in the field of computer vision, according to the scientists.
"Human vision has undergone millions of years of evolution and our field is only 30 years old," explained Professor Keren.
"At this stage computers still have difficulty doing things that are very simple for people, for example, recognising a picture of a human face.
"A computer has difficulty identifying when a picture is of a human face or how many faces are in a picture. However, computers are very good at simulating and sketching 3D images like the arteries in the brain or a road network."
Share this page
Email this page
Back to Top
Home
Edit Post
0 comments: