New software 'teaches' computers how to identify beauty

Jun 05, 2006

Beauty is no longer just in the eye of the beholder-computers "taught" to evaluate photographs can match people's aesthetic judgments of "beautiful" or "pretty" more than 70 percent of the time, according to Penn State researchers.

The researchers have developed a computational-aesthetics software that enables computers to single out aesthetically pleasing photographs based on more than a dozen visual features.

The software holds promise for Web users who, when searching for images, might want to hone in on what's "best" rather than browsing through thousands of returned images. It also has potential application for digital cameras. The software could inform photographers that they need to improve shot composition before they snap a picture, the researchers said.

"The software trains computers to judge photographs on 56 different visual features such as color saturation, exposure and composition," said James Wang, assistant professor in the College of Information Sciences and Technology (IST). "On average, if people think something is a 'good' picture, our computer thinks so, too."

The new software is described in a paper, "Studying Aesthetics in Photographic Images Using a Computational Approach," presented at the recent European Conference on Computer Vision in Graz, Austria. In addition to Wang, the other researchers involved in the project include Ritendra Datta and Dhiraj Joshi, doctoral students at Penn State, and Jia Li, assistant professor of statistics.

Aesthetics or people's conceptions of beauty are generally considered highly subjective. But, while no single standard for beauty exists, certain visual features of photographs have been identified as generally pleasing. These include contrast, perspective and texture as well as color saturation, exposure and composition.

To develop their software, the researchers used more than 3,500 images found on an online photo-sharing community which has more than 400,000 registered members. The researchers took advantage of members' rating of photographs for aesthetics. The rating was based on a scale of one to seven.

For their project, the researchers selected images which had been ranked by at least two members and which had aesthetics scores greater than 5.8 or less than 4.2. Using those images and rankings, the researchers "trained" the computer to identify 15 features most often correlated to high aesthetic scores.

"These image-annotation techniques that we are developing have potential for additional uses for judging photographs but also for other applications such as biomedical image databases," Wang said. "Computers, for instance, could be trained to classify pathologies."

Source: Penn State

Explore further: Voice synthesis software delivers high-quality singing automatically

Related Stories

How parents threaten children's online privacy

May 13, 2015

Most parents go to great lengths to keep their children safe online—but what if parents themselves, through the simple act of posting photos to Facebook and Instagram, are putting their own kids at risk ...

Many uses in researching quantum dots

May 04, 2015

It's easier to dissolve a sugar cube in a glass of water by crushing the cube first, because the numerous tiny particles cover more surface area in the water than the cube itself. In a way, the same principle applies to the ...

Recommended for you

First smartphone app that predicts GPA created

May 26, 2015

If you're a college student wondering how your study and party habits will affect your GPA, wonder no longer. Dartmouth researchers and their colleagues have built the first app that automatically predicts ...

Detecting and blocking leaky Android apps

May 22, 2015

Nine times out of ten, that Android app is connecting to multiple internet destinations without your knowledge, more than half of them require access to the sensitive, personal information on your mobile device in order to ...

User comments : 0

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.