• News
  • Learning in Machines & Brains

Pixel powerhouse

by Brian Lin Feb 28 / 14

When Senior Fellow David Lowe first wrote a computer algorithm to identify objects in images, he never envisioned it popping up on nearly half a million iPhones and in supermarket checkout lines.

Sony’s AIBO dog, which can see shapes thanks to David Lowe’s software.
Photo courtesy of Alden Chadwick/Flickr

But since its research publication in 1999, the Scale-Invariant Feature Transform (SIFT) algorithm, developed by Lowe, a professor at the University of British Columbia, has been licensed by more than 20 companies, making it the most widely adopted invention in University of British Columbia history.

“My interest at the time was to solve a long-standing research problem in the field of computer vision,” recalls Lowe, a member of CIFAR’s program in Neural Computation & Adaptive Perception, and a professor in UBC’s Department of Computer Science. “If we take a picture of an object, how does the computer recognize the same object in a different image, where the size, orientation or brightness may have changed?”

SIFT quickly caught the attention of Sony, which was making its foray into high-tech toys with AIBO the robot dog. SIFT gave AIBO sight, enabling it to recognize shapes on cue cards and perform corresponding tasks.

From robot dogs to smartphones

Then Lowe and his then graduate student Matthew Brown created AutoStitch, the world’s first fully automatic image-stitcher, which creates panoramic images from multiple shots. Cloudburst Research was formed to build an iPhone and iPad app based on AutoStitch, and has recently released an Android version.

Since then, the algorithm has found its way into supermarket anti-theft systems – by matching images of products in shopping carts to those on store shelves – and most recently in tools that assist visually impaired users. One licensee integrated it into an electronic magnifier to bring images from lecture theatre screens onto laptops; another company uses SIFT to identify paper currency and confirm its denomination, and is now developing a tool that scans a kitchen to create an inventory of its contents while helping users distinguish between similarly shaped items such as cans of soup.

“It’s very gratifying to see my work out there improving people’s daily lives in ways I had not anticipated,” says Lowe.

Lowe says his current research has benefitted from all he’s learned over 10 years in the Learning in Machines & Brains (LMB) program (formerly known as Neural Computation & Adaptive Perception). He’s been working to scale up recognition to handle a large number of images that may have wide ranging applications. “I’ve been quite interested in, for example, if you had images of every building in a city, could you take just one picture and recognize which one it is?”

The future was made in Canada

With computing power growing at an explosive pace, Lowe sees great potential for computer vision technology to make an even bigger impact in the foreseeable future — a future for which he says CIFAR has paved the way.

“The future of computer vision is exactly in the direction that the CIFAR group has pioneered, which is machine learning, and, in particular, deep learning,” Lowe said.

“Canada has actually been the country, more than any other, which has founded this field of deep learning.”

Lowe says the technologies we anticipate in years to come, such as improved vision for self-driving cars, took root in the work of Canadian researchers such as Geoffrey Hinton, the founding director of the LMB program, whose work on deep learning recently landed him a position with Google.

“LMB is really the founding research group that has created the field of deep learning,” Lowe said.