With a constructive knowledge-based theory of perception as its foundation, this paper starts with a review and critique of some artificial-intelligence programs that purport to see. It is then argued that these computer programs for scene analysis offer the hope of providing a more adequate account of human competence in interpreting line drawings as polyhedra than do the current psychological theories. This thesis has several aspects. The one emphasized here is that those programs have explored a variety of methods of incorporating a priori knowledge of objects through the use of models. After outlining the range of models used, presenting a set of criteria for evaluating the use of model information, and sketching some psychological theories, the various proposals are contrasted. This discussion leads to two new proposals for exploiting model information that involve elaborations of an existing program, POLY.
Get full access to this article
View all access options for this article.
References
1.
AttneaveFFrostR, 1969“The determination of perceived tridimensional orientation by minimum criteria”Perception and Psychophysics6391–396
2.
BartlettF C, 1967Remembering (London: Cambridge University Press)
ClowesM B, 1972a“Scene analysis and picture grammars” in Graphic Languages Eds NakeFRosenfeldA, (Amsterdam: North-Holland) pp 70–82
5.
ClowesM B, 1972b“Artificial intelligence as psychology”AISB Bulletin1 November
6.
FalkG, 1972“Interpretation of line data as a three-dimensional scent”Artificial Intelligence3 (2) 101–144
7.
GregoryR L, 1974Concepts and Mechanisms of Perception (New York: Charles Scribner's Sons)
8.
GuzmanA, 1968“Decomposition of a visual scene into three-dimensional bodies”AFIPS Proceedings of the Fall Joint Computer Conference33291–304
9.
HochbergJ, 1968“In the mind's eye” in Contemporary Theory and Research in Visual Perception Ed. HaberR N, (New York: Holt, Rinehart and Winston) pp 309–331
10.
HochbergJBrooksV, 1960“The psychophysics of form: Reversible-perspective drawings of spatial objects”American Journal of Psychology73337–354
11.
HuffmanD A, 1971“Impossible objects as nonsense sentences”Machine Intelligence 6 Eds MeltzerBMichieD, (Edinburgh: Edinburgh University Press) pp 295–323
12.
KopfermanH, 1930“Psychologische Untersuchungen über die Wirkung zweidimensionaler Darstellungen körperlicher Gebilde”Psychologische Forschung13293–364
13.
MackworthA K, 1973“Interpreting pictures of polyhedral scenes”Artificial Intelligence4 (2) 121–137
14.
MackworthA K, 1974a“On the interpretation of drawings as three-dimensional scenes”Ph. D. Thesis (unpublished), Laboratory of Experimental Psychology, University of Sussex, Brighton, England
15.
MackworthA K, 1974b“Using models to see”Proceedings of the AISB Summer Conference pp 127–137
16.
MackworthA K, 1975a“Consistency in networks of relations” technical report 75–3, Department of Computer Science, University of British Columbia
17.
MackworthA K, 1975b“How to see a simple world” technical report 75–4, Department of Computer Science, University of British Columbia
18.
MichieD M, 1974“On not seeing things” in On Machine Intelligence (New York: John Wiley) pp 112–133
19.
MinskyM L, 1975“A framework for representing knowledge” in Winston (1975) pp 211–277
20.
MinskyM LPapertJ S, 1972“Progress report” AI memorandum 252, Massachusetts Institute of Technology, Cambridge, Mass
21.
PenroseL SPenroseR, 1958“Impossible objects: A special type of illusion”British Journal of Psychology4931–33
22.
RobertsL G, 1965“Machine perception of three-dimensional objects” in Optical and Electro-optical Information Processing Eds TippettJ TBerkowitzD AClappL CKoesterC JVanderburghA, (Cambridge, Mass.: MIT Press) pp 159–197
23.
ShepardR NMetzlerJ, 1971“Mental rotation of three-dimensional objects”Science171701–703
24.
SouthallJ P C, (Ed.), 1962‘Helmholtz’ Treatise on Physiological Opticsvolume III (New York: Dover)
25.
SutherlandN S, 1973“Some comments on the Lighthill report and on Artificial Intelligence” in Artificial Intelligence: A Paper Symposium (London: Science Research Council) pp 22–31
26.
WaltzD L, 1972“Generating semantic descriptions from drawings of scenes with shadows”, MAC AI-TR-271, Massachusetts Institute of Technology, Cambridge, Mass. [Also in Winston (1975) pp 19–91]
27.
WinogradT, 1972“Procedures as representation for data in a computer program for understanding natural language” MAC AI-TR-84, Massachusetts Institute of Technology, Cambridge, Mass
28.
WinstonP H, 1968“Holes” AI memorandum 163, Massachusetts Institute of Technology, Cambridge, Mass
29.
WinstonP H, 1970“Learning structural descriptions from examples”, MAC AI-TR-76, Massachusetts Institute of Technology, Cambridge, Mass. [Also in Winston (1975) pp 157–209]
30.
WinstonP H, 1973“The MIT robot”Machine Intelligence 7 Eds MeltzerBMichieD, (Edinburgh: Edinburgh University Press) pp 431–463
31.
WinstonP H, (Ed.), 1975The Psychology of Computer Vision (New York: McGraw-Hill)
