New Smartphone App Tags Photos Automatically
Students from Duke University and the University of South Carolina have developed a smartphone app that they say automatically tags photos.
The app, called TagSense, debuted at the Association for Computing Machinery’s International Conference on Mobile Systems, Applications and Services in Washington, D.C. Developers of the app say TagSense offers “greater sophistication” in tagging photos than Apple’s iPhoto and Google’s Picasa.
The app currently is a prototype. Researchers said a public version of the app could be available in a few years.
“In our system, when you take a picture with a phone, at the same time it senses the people and the context by gathering information from all the other phones in the area,” Xuan Bao, a doctoral student in computer science at Duke, said in a university news release.
Bao collaborated on the app with Chuan Qin, a doctoral student from the University of South Carolina, in conjunction with Romit Roy Choudhury, assistant professor of electrical and computer engineering at Duke’s Pratt School of Engineering. Qin and Bao are summer interns at Microsoft.
“Phones have many different kinds of sensors that you can take advantage of,” Qin said. “They collect diverse information like sound, movement, location and light. By putting all that information together, you can sense the setting of a photograph and describe its attributes.”
Through use of information about the environment of a photo, the students think their app can achieve more accurate tagging of a picture than could be gained with facial recognition alone.
A smartphone’s built-in technology can tell whether a person is standing still for a posed photo, bowling or even dancing. Light sensors in the phone’s camera can figure out whether the shot is being taken indoors or outdoors on a sunny or cloudy day. The sensors also can gauge environmental conditions, such as rain or snow, by looking up weather conditions at that time and location. The phone’s microphone can detect whether a person in the photo is laughing or talking.
With the app, all of those attributes then are assigned to a photo, and the picture automatically is tagged with various words.
Researchers envision that TagSense would be adopted by groups of people, such as friends, who would “opt in,” allowing their smartphones’ capabilities to be harnessed when members of a group are together. To protect privacy, TagSense would not request data from nearby phones that don’t belong to a certain group of users, developers said.
Researchers said they’ve tested the app on eight mobile phones; more than 200 app-tagged photos have been taken around the Duke campus.
Follow Technorati