Learning to Segment Images Using Dynamic Feature Binding

Despite the fact that complex visual scenes contain multiple, overlapping objects, people perform object recognition with ease and accuracy. One operation that facilitates recognition is an early segmentation process in which features of objects are grouped and labeled according to which ob(cid:173) ject they belong. Current computational systems that perform this oper(cid:173) ation are based on predefined grouping heuristics. We describe a system called MAGIC that learn. In many cases, MAGIC discovers grouping heuristics similar to those previously proposed, but it also has the capability of find(cid:173) ing nonintuitive structural regularities in images.