Recognizing categories, objects, and parts

I will describe an approach to the recognition of object categories and individual objects, as well as their parts and sub-parts at multiple levels. Staring with a collection of images illustrating examples of an object category, the scheme constructs a category representation, and then uses it to identify novel members of the category. The acquired object representation uses a hierarchy of shared features, selected by maximizing the information delivered for categorization. The learning process automatically extracts the part-structure of the category, and during recognition, novel members of the category are recognized, and their parts are detected and localized. Recognition of objects and their parts is obtained by a feed-forward sweep from low to high levels of the hierarchy, followed by a sweep from the high to low levels.