The ubiquitous bar codes on product packaging reliably convey item and price information at checkout scanners, but that’s about all they do. Now, researchers at the Media Lab have developed a new kind of very tiny bar code that can pack in hundreds of times more information. Shoppers scanning store shelves could read them with the help of an ordinary cell-phone camera, or they could inspect them by eye from less than an inch away. Ultimately, the technology could also be used in classrooms, business presentations, video games, or motion-capture systems.
The system relies on a novel way of communicating data optically, explains associate professor Ramesh Raskar, who leads the Media Lab’s Camera Culture group: information is encoded in the angle and brightness of light rays. The data tags, called Bokodes, include a tiny light-emitting diode, which directs light from the back of the tag through a printed pattern and then a lens. Rays of light coming from the tags vary in brightness according to your angle of view, allowing you to see different information depending on how you’re looking at the device. Future versions of the technology could be made reflective, so the LED would be unnecessary.
Media Lab postdoc Ankit Mohan unveiled the concept in August at Siggraph, the leading international conference and exhibition on computer graphics. Graduate student Grace Woo, SM ‘07; Shinsaku Hiura, a visiting professor from Osaka University; and postdoc Quinn Smithwick collaborated with Raskar and Mohan on the project.
The tiny labels are more than six millimeters thick but just three millimeters across–about the size of the @ symbol on a typical computer keyboard. They have several advantages over today’s bar codes, Mohan says. They can provide far more information (such as the complete nutrition label from a food product), and a cell-phone camera can be used to read them from a distance. Shoppers could even use theirphones to scan multiple items at once–making it easy to determine, for example, which product is cheaper, or which has the least fat per serving.
The system could also prove useful beyond stores. For instance, people listening to classroom lectures or business presentations could use an LED-equipped Bokode pointer to point at something on a screen, such as one of the answers to a multiple-choice question. A camera could scan the room to pick up the unique identifying data encoded in each pointer, so that the presenter could tell who pointed at the right thing. Museums could also use the tiny codes to add information to exhibit labels; viewers would use cell-phone cameras to decode them.
The prototype devices produced at the Media Lab currently cost about $5 each, but Raskar says the price could easily drop to five cents once they are produced in volumes of even just a few hundred units.
The dark secret behind those cute AI-generated animal images
Google Brain has revealed its own image-making AI, called Imagen. But don't expect to see anything that isn't wholesome.
The hype around DeepMind’s new AI model misses what’s actually cool about it
Some worry that the chatter about these tools is doing the whole field a disservice.
The walls are closing in on Clearview AI
The controversial face recognition company was just fined $10 million for scraping UK faces from the web. That might not be the end of it.
This horse-riding astronaut is a milestone in AI’s journey to make sense of the world
OpenAI’s latest picture-making AI is amazing—but raises questions about what we mean by intelligence.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.