Visual Recognition and Categorization on the Basis of Similarities to Multiple Class Prototypes

One of the difficulties of object recognition stems from the need to overcome the variability in object appearance caused by pose and other factors, such as illumination. The influence of these factors can be countered by learning to interpolate between stored views of the target object, taken under representative combinations of viewing conditions. Difficulties of another kind arise in daily life situations that require categorization, rather than recognition, of objects. Although categorization cannot rely on interpolation between stored examples, we show that knowledge of several representative members, or prototypes, of each of the categories of interest can provide the necessary computational substrate for the categorization of new instances. We describe a system that represents input shapes by their similarities to several prototypical objects, and show that it can recognize new views of the familiar objects, discriminate among views of previously unseen shapes, and attribute the latter to familiar categories.

[1]  Shimon Edelman,et al.  Similarity-based viewspace interpolation and the categorization of 3D objects , 1997 .

[2]  Nathan Intrator,et al.  Learning as Extraction of Low-Dimensional Representations , 1997 .

[3]  Hilary Buxton,et al.  A similarity-based method for the generalization of face recognition over pose and expression , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[4]  Peter E. Hart,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[5]  S. Edelman,et al.  On Similarity to Prototypes in 3D Object Representation , 1995 .

[6]  KanadeTakeo,et al.  Shape and motion from image streams under orthography , 1992 .

[7]  R. Nelson,et al.  Large-scale tests of a keyed, appearance-based 3-D object recognition system , 1998, Vision Research.

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

[9]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[10]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[11]  Tomaso Poggio,et al.  View-based Models of 3D Object Recognition and Class-specific Invariances , 1994 .

[12]  Tomaso A. Poggio,et al.  A bootstrapping algorithm for learning linear models of object classes , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Ronen Basri,et al.  Recognition by prototypes , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Wilhelm Burger,et al.  Recognition and learning with polymorphic structural components , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[15]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[16]  R N Shepard,et al.  Multidimensional Scaling, Tree-Fitting, and Clustering , 1980, Science.

[17]  T. Poggio.  A theory of how the brain might work. , 1990, Cold Spring Harbor symposia on quantitative biology.

[18]  David G. Lowe,et al.  Three-Dimensional Object Recognition from Single Two-Dimensional Images , 1987, Artif. Intell..

[19]  Shimon Edelman,et al.  Receptive field spaces and class-based generalization from a single view in face recognition , 1995 .

[20]  Hiroshi Murase,et al.  Learning and recognition of 3D objects from appearance , 1993, [1993] Proceedings IEEE Workshop on Qualitative Vision.

[21]  Stephen M. Kosslyn,et al.  Pictures and names: Making the connection , 1984, Cognitive Psychology.

[22]  Keiji Tanaka,et al.  Inferotemporal cortex and object vision. , 1996, Annual review of neuroscience.

[23]  Keiji Tanaka.  Inferotemporal cortex and higher visual functions , 1992, Current Opinion in Neurobiology.

[24]  R. Shepard,et al.  Perceptual-cognitive explorations of a toroidal set of free-form stimuli , 1973 .

[25]  Nathan Intrator,et al.  Complex cells and Object Recognition , 1997 .

[26]  Marcin Peski.  Categorization , 2006, Encyclopedic Dictionary of Archaeology.

[27]  Tomaso A. Poggio,et al.  Linear Object Classes and Image Synthesis From a Single Example Image , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[29]  Shimon Edelman,et al.  Similarity, Connectionism, and the Problem of Representation in Vision , 1997, Neural Computation.

[30]  Wayne D. Gray,et al.  Basic objects in natural categories , 1976, Cognitive Psychology.

[31]  T Poggio,et al.  View-based models of 3D object recognition: invariance to imaging transformations. , 1995, Cerebral cortex.

[32]  Shimon Edelman,et al.  Representation of similarity as a goal of early visual processing , 1995 .

[33]  Yali Amit,et al.  Shape Quantization and Recognition with Randomized Trees , 1997, Neural Computation.

[34]  I. Biederman,et al.  Surface versus edge-based determinants of visual recognition , 1988, Cognitive Psychology.

[35]  S Edelman,et al.  Representation is representation of similarities , 1996, Behavioral and Brain Sciences.

[36]  G W Humphreys,et al.  The Effects of Surface Detail on Object Categorization and Naming , 1989, The Quarterly journal of experimental psychology. A, Human experimental psychology.

[37]  Amnon Rapoport,et al.  Structures in the subjective lexicon , 1971 .

[38]  Shimon Ullman,et al.  A Pictorial Approach to Object Classification , 1991, IJCAI.

[39]  Shimon Ullman,et al.  Face Recognition: The Problem of Compensating for Changes in Illumination Direction , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[40]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[41]  Yuichiro Anzai.  1 – Recognition and Learning by a Computer , 1992 .

[42]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

[43]  S. Edelman.  Receptive Fields for Vision: from Hyperacuity to Object Recognition , 1995 .

[44]  Bernt Schiele,et al.  Object Recognition Using Multidimensional Receptive Field Histograms , 1996, ECCV.

[45]  S. Edelman.  Representation of Similarity in 3D Object Discrimination , 1995 .

[46]  Tomaso A. Poggio,et al.  Just One View: Invariances in Inferotemporal Cell Tuning , 1997, NIPS.

[47]  Bartlett W. Mel.  SEEMORE: Combining Color, Shape, and Texture Histogramming in a Neurally Inspired Approach to Visual Object Recognition , 1997, Neural Computation.

[48]  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.

[49]  Keiji Tanaka,et al.  Optical Imaging of Functional Organization in the Monkey Inferotemporal Cortex , 1996, Science.

[50]  Tomaso Poggio,et al.  Observations on Cortical Mechanisms for Object Recognition and Learning , 1993 .

[51]  Shimon Edelman,et al.  Representation of objective similarity among three-dimensional shapes in the monkey , 1998, Biological Cybernetics.

[52]  Shimon Edelman,et al.  Representation, similarity, and the chorus of prototypes , 1993, Minds and Machines.

[53]  Takeo Kanade,et al.  Shape and motion from image streams under orthography: a factorization method , 1992, International Journal of Computer Vision.

[54]  Heinrich H. Bülthoff,et al.  Psychophysical support for a 2D view interpolation theory of object recognition , 1991 .

[55]  James L. Crowley,et al.  Visual Recognition Using Local Appearance , 1998, ECCV.

[56]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[57]  S Edelman,et al.  Faithful representation of similarities among three-dimensional shapes in human vision. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

[58]  Eleanor Rosch,et al.  Principles of Categorization , 1978 .

[59]  David W. Jacobs,et al.  The Space Requirements of Indexing Under Perspective Projections , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[60]  T. Poggio,et al.  Recognition and Structure from one 2D Model View: Observations on Prototypes, Object Classes and Symmetries , 1992 .

[61]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[62]  K. Kanatani.  Group-Theoretical Methods in Image Understanding , 1990 .

[63]  Bernt Schiele,et al.  Probabilistic object recognition using multidimensional receptive field histograms , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[64]  T. Poggio,et al.  Observations on Cortical Mechanisms for Object Recognition and N 00014-93-1-0385 Learning N 00014-92-J-1879 NSF ASC-9217041-JTHOR ( S ) , 2022 .

[65]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[66]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[67]  Ronen Basri,et al.  Recognition by Linear Combinations of Models , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[68]  Shimon Edelman,et al.  On Learning to Recognize 3-D Objects from Examples , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[69]  EdelmanFlorin CutzuSharon Duvdevani-BarDept.  Similarity to reference shapes as a basis for shaperepresentationShimon , 1996 .

[70]  T Poggio,et al.  Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks , 1990, Science.

[71]  D. Kendall.  SHAPE MANIFOLDS, PROCRUSTEAN METRICS, AND COMPLEX PROJECTIVE SPACES , 1984 .

[72]  Jonathan Baxter,et al.  The Canonical Distortion Measure for Vector Quantization and Function Approximation , 1997, ICML.

[73]  Shimon Edelman,et al.  Learning to Recognize Faces from Examples , 1992, ECCV.

[74]  David S. Broomhead,et al.  Multivariable Functional Interpolation and Adaptive Networks , 1988, Complex Syst..