Predict people’s artistic tastes with a simple computer program


Do you like the thick brushstrokes and the soft color palette of impressionist paintings like Claude Monet? Or do you like the bright colors and abstract shapes of Rosco? While individual artistic tastes hold some mysteries, a new study from the California Institute of Technology shows that a simple computer program can accurately predict which painting a person will like.

New research published in the journal Natural human behaviorLeveraged Amazon Mechanical Turk’s crowdsourcing platform with over 1,500 volunteers to rate paintings in the Impressionist, Cubist, Abstract, and Colorfield genres.

The volunteers ‘responses were entered into a computer program, and after this training period, the computer was able to predict the volunteers’ artistic preferences much better than had happened by accident.

“I was surprised by this result because I thought the assessment of art was personal and subjective,” said Kiyohito Iigaya, postdoctoral researcher working in the lab of John Odhati, professor of psychology at the California Institute of Technology. . Said.

The results not only showed that computers can make these predictions, but also led to a new understanding of how people judge art.

“The important thing is that we have insight into the mechanisms that people use to make aesthetic decisions,” says Odherty. “That is, people seem to combine them using basic image features. This is the first step in understanding how the process works.

In this study, the team will break down the visual attributes of a painting into low-level characteristics (characteristics such as contrast, saturation, hue, etc.) and high-level characteristics that require human judgment and include: I programmed the computer. Characteristics such as whether the painting is dynamic or stationary.

Computer programs then estimate how much a particular feature is taken into account in deciding how much you like a particular piece of art. Low-level and high-level functionality are combined to make these decisions. When the computer evaluates it, it can successfully predict its preference for another work of art that has not been seen before. “

Kiyohito Iigaya, senior author, postdoctoral fellow

The researchers also found that volunteers tend to fall into three general categories. People who like paintings using real objects, such as impressionist paintings. Someone who loves colorful abstract paintings like Rosco. People who like intricate paintings, like Picasso’s cubist portraits. The vast majority of people fell into the first “real” category. “A lot of people liked Impressionist paintings,” Iigaya explains.

In addition, the researchers found that deep convolutional neural networks (DCNNs) can be trained to learn to predict the artistic preferences of volunteers with a similar level of precision. DCNN is a type of machine learning program that provides a computer with a series of training images to help you learn the classification of objects such as cats and dogs. These neural networks have interconnected units, like neurons in the brain. Networks can “learn” by changing the strength of connection from one unit to another.

In this case, the deep learning approach did not include the selected low or high level visual characteristics used in the first part of the study. had.

“Deep neural network models learn exactly like the real brain, so we can’t really know exactly how the network solves a particular task,” Iigaya explains. Make. “It can be very strange, but when I looked inside the neural network, I found that it was building the same functional category that I had chosen. These results determine aesthetic preferences. This suggests that the functions used to do this may appear naturally in a brain-like architecture.

“We are now actively investigating whether this is the case by examining people’s brains while people are making the same kinds of decisions,” says Odherty.

In another part of the study, the researchers also showed that their simple computer program, already trained on artistic tastes, could accurately predict which photo the volunteers would like.

They showed the volunteers pictures of scenes such as swimming pools and food, and saw painting-like results. What’s more, the researchers have shown that reversing the order is also effective. After first training volunteers in photography, they were able to use the program to accurately predict the subject’s artistic preferences.

Computer programs have been successful in predicting the artistic tastes of volunteers, but researchers say there is still a lot to learn about the nuances that go into personal tastes.

“Some aspects of preference are unique to a particular individual and have not been successfully explained using this method,” says O’Doherty.

“This more particular element can be linked to semantic characteristics or to other personal characteristics that can affect the meaning, past experience and evaluation of the painting. Computer model. It may be possible to identify and learn these characteristics, but doing so is a personal preference in a way that may not be generalized among individuals, as we have seen here. Includes a more detailed study of. “


Journal reference:

Kenichi Iigaya, et al.. (2021) Aesthetic preference for art can be predicted from a mixture of low and high levels of visual characteristics. Natural human behavior..

Source link


About Author

Leave A Reply