Structuring Domain Knowledge For Visual Perception

E a r l y v i s u a l p rocess ing i s con jec tu red t o be almost e n t i r e l y domainindependent and d a t a d r i v e n ; however, h i g h l e v e l v i s i o n must e x p l o i t domain and o b j e c t s p e c i f i c c o n s t r a i n t s and methods, i n t e r m i n g l i n g d a t a d r i v e n and mode l -d r i ven r e c o g n i t i o n . We are concerned w i t h knowledge r e p r e s e n t a t i o n and i t s use f o r h i g h l e v e l v i s i o n . Th i s communication is a b r i e f r e p o r t on the theory u n d e r l y i n g Mapsee2, a second program fo r i n t e r p r e t i n g ske tch maps.