A Computational Model of Human Vision Based on Visual Routines

We argue that human vision has natural timescales, and that models of human vision at these different timescales are qualitatively different. In particular, at the timescale of a few seconds, human vision can be modeled in terms of two primitive functional routines. A “what” routine determines object identity from a segmented input and a “Where” routine determines the retinal location of a desired object. More complicated functions can be composed from these two. In particular, a complicated visuo-motor task such as copying can be described in terms of these two routines. The primary subroutine needed is one that computes the relationship of the parts of an object with respect to an object-centered frame.

[1]  Rajesh P. N. Rao,et al.  An Active Vision Architecture Based on Iconic Representations , 1995, Artif. Intell..


[3]  H. Barlow Vision: A computational investigation into the human representation and processing of visual information: David Marr. San Francisco: W. H. Freeman, 1982. pp. xvi + 397 , 1983 .

[4]  D. Ballard,et al.  Object recognition using steerable filters at multiple scales , 1993, [1993] Proceedings IEEE Workshop on Qualitative Vision.

[5]  Steven J. Nowlan,et al.  Maximum Likelihood Competitive Learning , 1989, NIPS.

[6]  Allen Gersho,et al.  Competitive learning and soft competition for vector quantizer design , 1992, IEEE Trans. Signal Process..

[7]  S. Ullman Visual routines , 1984, Cognition.

[8]  Leslie S. Smith,et al.  The principal components of natural images , 1992 .

[9]  Rajesh P. N. Rao,et al.  Object indexing using an iconic sparse distributed memory , 1995, Proceedings of IEEE International Conference on Computer Vision.

[10]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Rajesh P. N. Rao,et al.  Learning Saccadic Eye Movements Using Multiscale Spatial Filters , 1994, NIPS.

[12]  Helge J. Ritter,et al.  Neural computation and self-organizing maps - an introduction , 1992, Computation and neural systems series.

[13]  Vladimir Cherkassky,et al.  Self-Organization as an Iterative Kernel Smoothing Process , 1995, Neural Computation.

[14]  Oscar Firschein,et al.  Readings in computer vision: issues, problems, principles, and paradigms , 1987 .

[15]  S. Nayar,et al.  Learning and Recognition of 3-D Objects from Brightness Images * , 1993 .

[16]  Pentti Kanerva,et al.  Sparse Distributed Memory , 1988 .

[17]  A. Newell Unified Theories of Cognition , 1990 .