Assistant Professors Hao Jiang and Stella Yu said their linear solution -- which works at 10 times the speed of earlier methods -- has direct applications in the fields of action and object recognition, surveillance, wide-base stereo microscopy and three-dimensional shape reconstruction.
Jiang and Yu developed a linear algorithm to streamline the computer's work. Previously, computer visualization relied on software that captured a live image then hunted through millions of possible object configurations to find a match, they said. Further compounding the challenge was the fact that even more images needed to be searched as objects moved, altering scale and orientation.
Rather than combing through the image bank -- a time- and memory-consuming computing task -- Jiang and Yu said they turned to the mechanics of the human eye to give computers better vision.
"When the human eye searches for an object it looks globally for the rough location, size and orientation of the object," said Jiang. "Then it zeros in on the details. Our method behaves in a similar fashion ... ."
Jiang is to present his team's findings this week in Miami during the IEEE 2009 Conference on Computer Vision and Pattern Recognition.