Connectionist models and parallelism in high level vision

Students of human and machine vision share the belief that massively parallel processing characterizes early vision. For higher levels of visual organization, considerably less is known and there is much less agreement about the best computational view of the processing. This paper lays out a computational framework in which all levels of vision can be naturally carried out in highly parallel fashion. One key is the representation of all visual information needed for high level processing as discrete parameter values which can be represented by units. Two problems that appear to require sequential attention are described and their solutions within the basically parallel structure are presented. Some simple program results are included.

[1]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[2]  T. Poggio,et al.  Ill-Posed Problems and Regularization Analysis in Early Vision , 1984 .

[3]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[4]  Marvin Minsky,et al.  K-Lines: A theory of Memory , 1980, Cogn. Sci..

[5]  M. Posner.  Chronometric explorations of mind , 1978 .

[6]  Daniel Sabbah.  Computing with connections in visual recognition of origami objects , 1985 .

[7]  David C. Plaut,et al.  Visual Recognition of Simple Objects by a Connection Network. , 1984 .

[8]  Wayne A. Wickelgren,et al.  Chunking and consolidation: A theoretical synthesis of semantic networks configuring in conditioning , 1979 .

[9]  Dana H. Ballard,et al.  Viewframes: A Connectionist Model of Form Perception, , 1983 .

[10]  Geoffrey E. Hinton.  Shape Representation in Parallel Systems , 1981, IJCAI.

[11]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Dana H. Ballard,et al.  Parameter Nets , 1984, Artif. Intell..

[13]  C M Brown,et al.  Computer Vision and Natural Constraints , 1984, Science.

[14]  Alex Pentland,et al.  Shading into Texture , 1984, Artif. Intell..

[15]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[16]  Takeo Kanade,et al.  A Theory of Origami World , 1979, Artif. Intell..

[17]  M. Just,et al.  Eye fixations and cognitive processes , 1976, Cognitive Psychology.

[18]  Daniel Sabbah,et al.  Design Of A Highly Parallel Visual Recognition System , 1981, IJCAI.

[19]  Lokendra Shastri,et al.  Semantic Networks and Neural Nets , 1984 .

[20]  Marvin Minsky,et al.  A framework for representing knowledge , 1974 .

[21]  H. Barrow,et al.  RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES , 1978 .

[22]  Scott E. Fahlman,et al.  The hashnet interconnection scheme , 1980 .

[23]  C. Cotman,et al.  Synapse replacement in the nervous system of adult vertebrates. , 1981, Physiological reviews.

[24]  M. Posner,et al.  Components of visual orienting , 1984 .

[25]  S. Kosslyn,et al.  Coordinate systems in the long-term memory representation of three-dimensional shapes , 1983, Cognitive Psychology.

[26]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[27]  J. Feldman.  Four frames suffice: A provisional model of vision and space , 1985, Behavioral and Brain Sciences.

[28]  A G Barto,et al.  Toward a modern theory of adaptive networks: expectation and prediction. , 1981, Psychological review.

[29]  P. Thompson,et al.  Margaret Thatcher: A New Illusion , 1980, Perception.

[30]  Geoffrey E. Hinton.  A Parallel Computation that Assigns Canonical Object-Based Frames of Reference , 1981, IJCAI.

[31]  Geoffrey E. Hinton,et al.  Parallel visual computation , 1983, Nature.

[32]  A. Treisman.  The Role of Attention in Object Perception , 1983 .