A Framework for Generic Object Recognition with Bayesian Networks

J.M. Liang, J.Q. Liang, and Q.L. Ren


  1. [1] I. Biederman, Human image understanding: Recent researchand a theory, Computer Vision, Graphics and Image Processing, 32, 1985, 29–73. doi:10.1016/0734-189X(85)90002-7
  2. [2] I. Biederman, Recognition-by-components: A theory of humanimage understanding, Psychological Review, 94, 1987, 115–147. doi:10.1037/0033-295X.94.2.115
  3. [3] S.J. Dickinson, R. Bergevin, I. Biederman, J.O. Eklundh,R. Munck-Fairwood, & A. Pentland, The use of geons for genericobject recognition, Proc. 13th Int. Joint Conf. on ArtificialIntelligence, Chambery, France, August 1993, 1693–1699.
  4. [4] R. Bergevin & M.D. Levine, Generic object recognition: Building and matching coarse description from line drawings, IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(1), 1993, 19–36. doi:10.1109/34.184772
  5. [5] S.J. Dickinson, A.P. Pentland, & A. Rosenfeld, 3-D shape recovery using distributed aspect matching, IEEE Trans. on Pattern Analysis and Machine Intelligence, 14(2), 1992, 174–198. doi:10.1109/34.121788
  6. [6] S.J. Dickinson, A.P. Pentland, & A. Rosenfeld, From volumesto views: An approach to 3-D object recognition, CVGIP:Image Understanding, 55(2), 1992, 130–154. doi:10.1016/1049-9660(92)90013-S
  7. [7] J.E. Hummel & I. Biederman, Dynamic binding in a neuralnetwork for shape recognition, Psychological Review, 99(3),1992, 480–517. doi:10.1037/0033-295X.99.3.480
  8. [8] R.C. Fairwood, Recognition of generic components usinglogic–program relations of image contours, Image and VisionComputing, 9(2), 1991, 113–122. doi:10.1016/0262-8856(91)90021-G
  9. [9] J. Pearl, Probabilistic reasoning in intelligent systems (SanMateo, CA: Morgan Kaufmann, 1988).
  10. [10] F.V. Jensen, H.I. Christensen, & J. Nielsen, Bayesian methodsfor interpretation and control in multi-agent vision systems,SPIE: Proc. of Applications of AI X: Machine Vision andRobotics, Orlando, FL, April 1992, 536–548. doi:10.1117/12.58599
  11. [11] F.V. Jensen & J. Liang, drHugin: A system for hypothesisdriven data request, in A. Gammerman (ed.), Probabilisticreasoning and Bayesian belief networks (Henley on Thames,Oxon: Alfred Waller, 1995).
  12. [12] T.S. Levitt, Model-based probabilistic inference in hierarchicalhypothesis, in J.F. Lemmer & L.N. Kanal (eds.), Uncertaintyin artificial intelligence (Amsterdam: North-Holland, 1986).
  13. [13] T.S. Levitt, Bayesian inference for radar image based surveillance, in J.F. Lemmer & L.N. Kanal, Uncertainty in artificialintelligence 2 (New York: North-Holland, 1988).
  14. [14] J.M. Agosta, Probabilistic recognition networks: An application of influence diagrams to visual recognition, Technical Report (doctoral diss.), Stanford University, Stanford, CA, 1991.
  15. [15] T.O. Binford, T.S. Levitt, & W.B. Mann, Bayesian inference inmodel-based machine vision, in L.N. Kanal, T.S. Levitt, & J.F.Lemmer, Uncertainty in artificial intelligence 3 (Amsterdam:North-Holland, 1989), 73–95.
  16. [16] T.S. Levitt, J.M. Agosta, & T.O. Binford, Mode-based influence diagrams for machine vision, in M. Henrion, R.D. Shachter, L.N. Kanal, & J.F. Lemmer (eds.), Uncertainty in artificial intelligence 5 (Amsterdam: North-Holland, 1990).
  17. [17] T.S. Levitt, T.O. Binford, & G.J. Ettinger, Utility-basedcontrol for computer vision, in R.D. Shachter, T.S. Levitt,L.N. Kanal, & J.F. Lemmer (eds.), Uncertainty in artificial intelligence 4 (New York: Elsevier Science Publishing Company Inc., 1990).
  18. [18] R. Rimey & C.M. Brown, Control of selective perceptionusing Bayes nets and decision theory, International Journalof Computer Vision, 12(2/3), 1994, 173–209. doi:10.1007/BF01421202
  19. [19] R.C. Munck-Fairwood, Recognition of geometric primitivesusing logic program and probabilistic network reasoningmethods, SPIE: Proc. of Applications of AI X: Machine Visionand Robotics, Orlando, FL, April 1992, 589–600. doi:10.1117/12.58604
  20. [20] S. Sarkar & K.L. Boyer, Integration, inference, and management of spatial information using Bayesian networks: Perceptual organization, IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(3), 1993, 256–274. doi:10.1109/34.204907
  21. [21] V. Kumar & U. Desai, Image interpretation using Bayesiannetworks, IEEE Trans. on Pattern Analysis and MachineIntelligence, 18(1), 1996, 74–77. doi:10.1109/34.476423
  22. [22] M. Marengoni, C. Jaynes, A. Hanson, & E. Riseman, AscenderII: A visual framework for 3D reconstruvtion, Int. Conf. onComputer Vision Systems, Las Palmas Gran Canaria, Spain,January 1999, 469–488. doi:10.1007/3-540-49256-9_28
  23. [23] M. Marengoni, A. Hanson, S. Zilberstein, & E. Riseman,Control in a 3D reconstruction system using selective perception, 7th Int. Conf. on Computer Vision, Kerkyra, Greece, September 1999, 1229–1236.
  24. [24] S. Wachsmuth, H. Brandt-Pook, G. Socher, F. Kummert, &G. Sagerer, Multilevel integration of vision and speech understanding using Bayesian networks, Int. Conf. on Computer Vision Systems, Las Palmas Gran Canaria, Spain, January 1999, 231–254. doi:10.1007/3-540-49256-9_15
  25. [25] H. Buxton & S. Gong, Advanced visual surveillance usingBayesian networks, IEEE Workshop on Context-based Vision,Cambridge, MA, June 1995, 111–123.
  26. [26] K. Basye, T. Dean, J. Kirman, & M. Lejter, A decision-theoretic approach to planning, perception, and control, IEEEEXPERT, 7(4), 1992, 58–65. doi:10.1109/64.153465
  27. [27] T.L. Dean & M. Wellman, Planning and control (San Mateo,CA: Morgan Kaufmann, 1991).
  28. [28] A.E. Nicholson & J.M. Brady, Sensor validation using dynamicbelief networks, in D. Dubois, M.P. Wellman, B. D’Ambrosio,& P. Smets (eds.), Uncertainty in artificial intelligence (SanFrancisco: Morgan Kaufmann Publishers, 1992).
  29. [29] V. Pavlović, J.M. Rehg, T.-J. Cham, & K.P. Murphy, Adynamic Bayesian network approach to figure tracking usinglearned dynamic models, 7th Int. Conf. on Computer Vision,Kerkyra, Greece, September 1999, 94–101.
  30. [30] R. Bhatnagar & L.N. Kanal, Structural and probabilisticknowledge for abductive reasoning, IEEE Trans. on PatternAnalysis and Machine Intelligence, 15(3), 1993, 233–245. doi:10.1109/34.204905
  31. [31] P.G. Ducksbury, Parallel texture region segmentation usinga Pearl Bayes network, Proc. British Machine Vision Conf.,London, UK, 1993, 188–195.
  32. [32] B. Krebs, M. Burkhardt, & B. Korn, A task driven 3d objectrecognition system using Bayesian networks, 6th Int. Conf. onComputer Vision, Bombay, India, January 1998, 527–532.
  33. [33] S.M. LaValle, A Bayesian framework for considering probability distribution of image segments and segmentations, Technical Report (master’s thesis), The Beckman Institute, University of Illinois, Urbana, IL, 1993.
  34. [34] S.A. Musman, L.W. Chang, & L.B. Booker, Application of areal-time control strategy for Bayesian belief networks to shipclassification problem solving, International Journal of PatternRecognition and Artificial Intelligence, 7(3), 1993, 513–526. doi:10.1142/S0218001493000261
  35. [35] L.E. Sucar & D.F. Gillies, Expressing relational and temporalknowledge in visual probabilistic networks, in D. Dubois,M.P. Wellman, B. D’Ambrosio, & P. Smets (eds.), Uncertaintyin artificial intelligence (San Francisco: Morgan KaufmannPublishers, 1992).
  36. [36] J.J. Koenderink & A.J. van Doorn, The internal representationof solid shape with respect to vision, Biological Cybernetics,32, 1979, 211–216. doi:10.1007/BF00337644
  37. [37] J. Pearl, Fusion, propagation, and structuring in beliefnetworks, Artificial Intelligence, 29, 1986, 241–288. doi:10.1016/0004-3702(86)90072-X
  38. [38] G.F. Cooper, Bayesian belief-network inference using recursive decomposition, Research Report KSL-90-05, Knowledge Systems Laboratory, Medical Computer Science, Stanford University, CA, 1990.
  39. [39] B. D’Ambrosio, Symbolic probabilistic inference in belief nets,Technical Report, Department of Computer Science, OregonState University, Corvallis, OR, 1989.
  40. [40] S.L. Lauritzen & D.J. Spiegelhalter, Local computations withprobabilities on graphical structures and their application toexpert systems, Journal of the Royal Statistical Society, SeriesB (Methodological), 50(2), 1988, 157–224.
  41. [41] R.D. Shachter, Evaluating influence diagrams, OperationsResearch, 34(6), 1986, 871–882.
  42. [42] G. Shafer & P.P. Shenoy, Probability propagation, Annals ofMathematics and Artificial Intelligence, 2, 1989, 327–352. doi:10.1007/BF01531015
  43. [43] R.D. Shachter, S.K. Andersen, & P. Szolovits, The equivalenceof exact methods for probabilistic inference on belief networks,Technical Report, Department of Engineering-Economic Systems, Stanford University, CA, October 1991.
  44. [44] G.F. Cooper, The computational complexity of probabilisticinference using Bayesian belief networks, Artificial Intelligence,42(2–3), 1990, 393–405. doi:10.1016/0004-3702(90)90060-D
  45. [45] P. Dagum & M. Luby, Approximating probabilistic inferencein Bayesian belief networks is NP-hard, Artificial Intelligence,60, 1993, 141–153. doi:10.1016/0004-3702(93)90036-B
  46. [46] F.V. Jensen, S.L. Lauritzen, & K.G. Olesen, Bayesian updating in causal probabilistic networks by local computations, Computational Statistics Quarterly, 4, 1990, 269–282.
  47. [47] F.V. Jensen, K.G. Olesen, & S.K. Andersen, An algebraof Bayesian belief universes for knowledge based systems,Networks, 20(5), 1990, 637–659. doi:10.1002/net.3230200509
  48. [48] S.K. Andersen, K.G. Olesen, F.V. Jensen, & F. Jensen,HUGIN—a shell for building Bayesian belief universes forexpert systems, Proc. 11th Int. Joint Conf. on ArtificialIntelligence, Detroit, MI, August 1989, 1080–1085.
  49. [49] J.G. Snodgrass & M. Vanderwart, A standardized set of260 pictures: Norms for name agreement, image agreement,familiarity, and visual complexity, Journal of ExperimentalPsychology, 6(2), 1980, 174–215.
  50. [50] A.P. Pentland, Perceptual organization and the representationof natural form, Artificial Intelligence, 28, 1986, 293–331. doi:10.1016/0004-3702(86)90052-4
  51. [51] S.J. Dickinson, S. Stevenson, E. Amdur, J. Tsotsos, &L. Olsson, Integrating task-directed planning with reactiveobject recognition, Proc. SPIE Intelligent Robotics andComputer Vision XII, Boston, MA, September 1993, 212–224. doi:10.1117/12.150138
  52. [52] D.D. Hoffman & W.A. Richards, Parts of recognition, Cognition, 18, 1985, 65–96. doi:10.1016/0010-0277(84)90022-2
  53. [53] J. Liang, H.I. Christensen, & F.V. Jensen, Qualitativerecognition using Bayesian reasoning, in E.S. Gelsema &L.N. Kanal (eds.), Pattern recognition in practice IV: Multiple paradigms, comparative studies and hybrid systems (Amsterdam: Elsevier, 1994).
  54. [54] L. Stark & K. Bowyer, Generic object recognition using formand function (Singapore: World Scientific Publishing Co, 1996).
  55. [55] J. Liang, Q. Ren, Z. Xu, & J. Fang, Causal networks and their toolkit in {KSE}, in B. Bouchon-Meunier, R.R. Yager, & L.A. Zadeh (eds.), Advances in intelligent computing (Berlin: Springer-Verlag, 1995), 139-148

Important Links:

Go Back