| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Achieving Generalized Object Recognition through Reasoning about Association of Function to Structure
October 1991 (vol. 13 no. 10)
pp. 1097-1104
An attempt is made to demonstrate the feasibility of defining an object category in terms of the functional properties shared by all objects in the category. This form of representation should allow much greater generality. A complete system has been implemented that takes the boundary surface description of a 3D object as its input and attempts to recognize whether the object belongs to the category 'chair' and, if so, into which subcategory if falls. This is, to the authors' knowledge, the first implemented system to explore the use of a purely function-based definition of an object category (that is, no explicit geometric or structural model) to recognize 3D objects. System competence has been evaluated on a database of over 100 objects, and the results largely agree with human interpretation of the objects.
[1] 1097M. Brady, P. E. Agre, D. J. Braunegg, and J. H. Connell, "The mechanics mate," inAdvances in Artificial Intelligence(T. O'Shea, Ed.). New York: Elsevier, 1985, pp. 79-94.[2] R. A. Brooks, and T. A. Binford, "Representing and reasoning about partially specified scenes," inProc. DARPA Image Understanding Workshop, 1980, pp. 95-103.[3] J. H. Connell and M. Brady, "Generating and generalizing models of visual objects,"Artificial Intell., vol. 31, pp. 159-183, 1987.[4] M. Di Manzo, E. Trucco, F. Giunchiglia, F. Ricci, "FUR: Understanding FUnctional Reasoning,"Int J. Intelligent Syst., vol. 4, pp. 431-457, 1989[5] Eastman Kodak Co.,Ergonomic Design for People at Work.New York: Van Nostrand Reinhold, 1983, vol. 1,[6] R. R. Goldberg and D. G. Lowe, "Verification of 3-D parametric models in 2-D image data," inProc. IEEE Workshop Comput. vision(Miami, FL), 1987, pp. 255-257.[7] W. E. L. Grimson, "On the recognition of parameterized 2D objects,"Int. J. Comput. Vision, vol. 3, pp. 353-312, 1988.[8] S. Ho, "Representing and using functional definitions for visual recognition," Ph. D. Dissertation, Univ. Wisconsin, Madison, 1987.[9] M. Minsky,The Society of Mind.New York: Simon and Shuster, 1985.[10] E. Rosch, C. B. Mervis, W. D. Gray, D. Johnson, P. Boyes-Braem, "Basic objects in natural categories,"Cognitive Psych., vol. 8, pp. 382-439, 1976.[11] L. Stark, and K. W. Bowyer, "Achieving generalized object recognition through reasoning about association of function to structure,"AAAI-90 Workshop Qualitative Vision(Boston, MA), July 1990, pp. 137-141.[12] L. Stark, L. O. Hall, and K. W. Bowyer, "An investigation of methods of combining functional evidence for 3-D object recognition," inProc. SPIE 1381: Intell. Robots Comput. Vision IX: Algorithms Techn.(Boston, MA), 1990.[13] P. H. Winston, T. O. Binford, B. Katz, and M. Lowry, "Learning physical description from functional definitions, examples, and precedents," inProc. Int. Symp. Robotics Research(M. Brady and R. Paul, Eds.). Cambridge, MA: MIT Press, 1984, vol. 1.[14] P. H. Winston, "Learning structural descriptions from examples," inThe Psychology of Computer Vision, P. H. Winston (Ed.). New York: McGraw-Hill, 1975.
Index Terms:
function/structure association; chair recognition; function-based object category definition; object recognition; reasoning; boundary surface description; computerised pattern recognition; computerised picture processing; inference mechanisms; knowledge based systems
Citation:
L. Stark, K. Bowyer, "Achieving Generalized Object Recognition through Reasoning about Association of Function to Structure," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 10, pp. 1097-1104, Oct. 1991, doi:10.1109/34.99242