Algorithm for identifying object boundaries in digital images 50,000 times more efficient than predecessor
Tuesday, May 31, 2011 - 06:30
in Mathematics & Economics
Determining the boundaries of objects is one of the central problems in computer vision. It's something humans do with ease: We glance out the window and immediately see cars as distinct from the sidewalk and street and the people walking by, or lampposts as distinct from the facades of the buildings behind them. But duplicating that facility in silicon has proven remarkably difficult.