00100	Categorize by goals (how many, how complex)
00200	  by objects(how many, how complex)
00300	  by knowledge available, required
00400	
00500	We discuss these issues in the context of some paradigms:
00600	PARADIGM 1:  We know what is in the visual environment, where the
00700	objects are, and remember colors and details of all objects.  Moreover,
00800	we know that nothing else is in the environment.
00900	PARADIGM 2:  We know some of the objects, and some loose spatial
01000	relations among them.  We do not know what else is in the environment.
01100	PARADIGM 3:  We are in a "known" environment, such as an ordinary office,
01200	or outside, with a complex set of goals, complex environment and
01300	rich universe of objects.
01400	PARADIGM 4: We are shown a photograph without knowing the context.
01500	
01600	In the first paradigm, if the goals are few and objects few,
01700	some relatively simple techniques may be used to recognize objects
01800	[Tenenbaum, Freuder].  A tlephone may be the only black object.  We
01900	note that Tenenbaum's work uses no shape information, only pointwise
02000	properties such as color, and depth from a ranging device.
02100	
02200	HOW WILL THESE GENERALIZE
02300	
02400	FUNDAMENTAL VISION PROBLEMS
02500	segmentation-body,part
02600	obscuration-indexing
02700	representation
02800	computational complexity
02900	linking-indexing
03000	description vs recognition
03100	use of context
03200	learning
03300	low level,bottom up  vs high level,top down
03400	
03500	How does each appear
03600	What are the options