Recognition by Linear Combinations of Models

An approach to visual object recognition in which a 3D object is represented by the linear combination of 2D images of the object is proposed. It is shown that for objects with sharp edges as well as with smooth bounding contours, the set of possible images of a given object is embedded in a linear space spanned by a small number of views. For objects with sharp edges, the linear combination representation is exact. For objects with smooth boundaries, it is an approximation that often holds over a wide range of viewing angles. Rigid transformations (with or without scaling) can be distinguished from more general linear transformations of the object by testing certain constraints placed on the coefficients of the linear combinations. Three alternative methods of determining the transformation that matches a model to a given image are proposed. >

[1]  D. Marr,et al.  Analysis of occluding contour , 1977, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[2]  S. Ullman,et al.  The interpretation of visual motion , 1977 .

[3]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[4]  D Marr,et al.  Directional selectivity and its use in early visual processing , 1981, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[5]  H. C. Longuet-Higgins,et al.  A computer algorithm for reconstructing a scene from two projections , 1981, Nature.

[6]  S. Ullman.  Recent Computational Studies in the Interpretation of Structure from Motion , 1983 .

[7]  W. Grimson,et al.  Model-Based Recognition and Localization from Sparse Range or Tactile Data , 1984 .

[8]  Irving Biederman,et al.  Human image understanding: Recent research and a theory , 1985, Comput. Vis. Graph. Image Process..

[9]  M. Hebert,et al.  The Representation, Recognition, and Locating of 3-D Objects , 1986 .

[10]  W. Eric L. Grimson,et al.  The combinatorics of local constraints in model-based recognition and localization from sparse data , 1984, JACM.

[11]  Shimon Ullman,et al.  An Approach to Object Recognition: Aligning Pictorial Descriptions , 1986 .

[12]  D. W. Thompson,et al.  Three-dimensional model matching from an unconstrained viewpoint , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[13]  Demetri Psaltis,et al.  Optical Neural Computers , 1987, Topical Meeting on Optical Computing.

[14]  R. Bajcsy,et al.  Three dimensional object representation revisited , 1987 .

[15]  J. K. Aggarwal,et al.  SHAPE RECOGNITION FROM SINGLE SILHOUETTES. , 1987 .

[16]  Yehezkel Lamdan,et al.  On recognition of 3-D objects from 2-D images , 2011, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[17]  Shimon Ullman,et al.  Aligning A Model To An Image Using Minimal Information , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[18]  Ronen Basri,et al.  The Alignment Of Objects With Smooth Surfaces , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[19]  Richard A. Andersen,et al.  A back-propagation programmed network that simulates response properties of a subset of posterior parietal neurons , 1988, Nature.

[20]  Thomas S. Huang,et al.  Motion and Structure from Orthographic Projections , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  S. Ullman.  Aligning pictorial descriptions: An approach to object recognition , 1989, Cognition.

[22]  R. Brockett.  Least squares matching problems , 1989 .

[23]  W. Eric L. Grimson,et al.  The Combinatorics of Heuristic Search Termination for Object Recognition in Cluttered Environments , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  W. Eric L. Grimson.  The Combinatorics of Heuristic Search Termination for Object Recognition in Cluttered Environments , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  久間 和生,et al.  OPTICAL NEURAL COMPUTING , 1991 .