Computational theories of object recognition
Trends in Cognitive SciencesPublished 1 November 1997
Shimon Edelman
Citations89
SJR quartileQ1
SJR score4.51
SNIP5.51
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper examines four current theoretical approaches to the representation and recognition of visual objects: structural descriptions, geometric constraints, multidimensional feature spaces and shape-space approximation.
Abstract
This paper examines four current theoretical approaches to the representation and recognition of visual objects: structural descriptions, geometric constraints, multidimensional feature spaces and shape-space approximation. The strengths and weaknesses of the four theories are considered, with a special focus on their approach to categorization - a computationally challenging task which is not widely addressed in computer vision, where the stress is rather on the generalization of recognition across changes of viewpoint.
Keywords
Computer Science
Journal of Cognitive NeuroscienceEigenfaces for Recognition
13,775 Citations1991Matthew Turk, Alex Pentland
A near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals, and that is easy to implement using a neural network architecture.
Pattern classification and scene analysis
12,643 Citations1973Richard O. Duda, Peter E. Hart
Signal detection theory and psychophysics
9,998 Citations1966David Marvin Green, John A. Swets
This book discusses statistical decision theory and sensory processes in signal detection theory and psychophysics and describes how these processes affect decision-making.
International Journal of Computer VisionColor indexing
5,592 Citations1991Michael J. Swain, Dana H. Ballard
It is demonstrated that color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models and that they can differentiate among a large number of objects.
Psychological ReviewRecognition-by-components: A theory of human image understanding.
5,507 Citations1987Irving Biederman
Recognition-by-components (RBC) provides a principled account of the heretofore undecided relation between the classic principles of perceptual organization and pattern recognition.
IEEE Transactions on Pattern Analysis and Machine IntelligenceApplication of the Karhunen-Loeve procedure for the characterization of human faces
2,454 Citations1990Michael Kirby, L. Sirovich
The use of natural symmetries (mirror images) in a well-defined family of patterns (human faces) is discussed within the framework of the Karhunen-Loeve expansion, which results in an extension of the data and imposes even and odd symmetry on the eigenfunctions of the covariance matrix.
Proceedings of the Royal Society of London. Series B, Biological sciencesRepresentation and recognition of the spatial organization of three-dimensional shapes
2,183 Citations1978David Marr, H. K. Nishihara
The human visual process can be studied by examining the computational problems associated with deriving useful information from retinal images by applying the approach to the problem of representing three-dimensional shapes for the purpose of recognition.
International Journal of Computer VisionVisual learning and recognition of 3-d objects from appearance
1,891 Citations1995Hiroshi Murase, Shree K. Nayar
A near real-time recognition system with 20 complex objects in the database has been developed and a compact representation of object appearance is proposed that is parametrized by pose and illumination.
The Annals of StatisticsOptimal Global Rates of Convergence for Nonparametric Regression
1,485 Citations1982Charles J. Stone
Bulletin of the London Mathematical SocietyShape Manifolds, Procrustean Metrics, and Complex Projective Spaces
1,478 Citations1984David G. Kendall
Cambridge University Press eBooksPerception as Bayesian Inference
1,468 Citations1996David C. Knill, David C. Knill +14 more
NatureComputational vision and regularization theory
1,414 Citations1985Tomaso Poggio, Vincent Torre +1 more
Descriptions of physical properties of visible surfaces, such as their distance and the presence of edges, must be recovered from the primary image data and algorithms and parallel analog circuits that can solve ‘ill-posed problems’ and which are suggestive of neural equivalents in the brain are proposed.
Annual Review of NeuroscienceInferotemporal Cortex and Object Vision
1,413 Citations1996Keiji Tanaka
Cells in area TE of the inferotemporal cortex of the monkey brain selectively respond to various moderately complex object features, and those that cluster in a columnar region that runs perpendicular to the cortical surface respond to similar features.
Annual Review of NeuroscienceVisual Object Recognition
1,314 Citations1996Nikos K. Logothetis, David L. Sheinberg
Evidence from the fields of psychology, neuropsychology, and neurophysiology supports the idea that there are multiple systems for recognition of objects, and indicates that one system may represent objects by combinations of multiple views, or aspects, and another may represent Objects by structural primitives and their spatial interrelationships.
Artificial IntelligenceThree-dimensional object recognition from single two-dimensional images
1,277 Citations1987David Lowe
It is argued that similar mechanisms and constraints form the basis for recognition in human vision.
Computer Vision Graphics and Image ProcessingPerceptual organization and visual recognition
1,031 Citations1985
Kluwer international series in engineering and computer sciencePerceptual Organization and Visual Recognition
978 Citations1985David Lowe
Spatial organization and recognition are shown to be a practical basis for current systems and to provide a promising path for further development of improved visual capabilities.
NatureA network that learns to recognize three-dimensional objects
936 Citations1990Tomaso Poggio, Shimon Edelman
A scheme is developed, based on the theory of approximation of multivariate functions, that learns from a small set of perspective views a function mapping any viewpoint to a standard view, and a network equivalent to this scheme will 'recognize' the object on which it was trained from any viewpoint.
Psychological ReviewDynamic binding in a neural network for shape recognition.
933 Citations1992John E. Hummel, Irving Biederman
A neural network is presented that generates a viewpoint-invariant structural description specifying the object's parts and the relations among them and uses synchrony to parse images into their constituent parts.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRecognition by linear combinations of models
817 Citations1991Shimon Ullman, Ronen Basri
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 and 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.
CognitionAligning pictorial descriptions: An approach to object recognition
572 Citations1989Shimon Ullman
The proposed alignment method also uses abstract description, but unlike structural description methods it uses them pictorially, rather than in symbolic structural descriptions.
Asilomar Conference on Signals, Systems and ComputersBasis pursuit
471 Citations1994Shaobing Chen, David L. Donoho
IEEE Transactions on Pattern Analysis and Machine IntelligenceLocalizing Overlapping Parts by Searching the Interpretation Tree
462 Citations1987W. Eric L. Grimson, Tomás Lozano‐Pérez
The approach operates by examining all hypotheses about pairings between sensed data and object surfaces and efficiently discarding inconsistent ones by using local constraints on distances between faces, angles between face normals, and angles of vectors between sensed points.
Bulletin of Mathematical BiologyBiometrics, biomathematics and the morphometric synthesis
434 Citations1996Fred L. Bookstein
The history and principal tools of this morphometric synthesis in their biomathematical and biometrical context are reviewed and their usefulness in a study of focal neuroanatomical anomalies in schizophrenia is demonstrated.
Journal of Experimental Psychology Human Perception & PerformanceIs human object recognition better described by geon structural descriptions or by multiple views? Comment on Biederman and Gerhardstein (1993).
401 Citations1995Michael J. Tarr, HH Bülthoff
The weight of current evidence supports an exemplar-based multiple-views mechanism as an important component of both exemplar specific and categorical recognition, the domain they are intended to explain.
Vision ResearchMechanisms of perceptual learning
397 Citations1999Barbara Anne Dosher, Zhong‐Lin Lu
Perceptual learning over 8-10 days improved the filtering or exclusion of external noise by a factor of two or more, and improved suppression of additive internal noise--equivalent to stimulus enhancement--by 50% or more.
Behavioral and Brain SciencesRepresentation is representation of similarities
380 Citations1998Shimon Edelman
A unified approach to visual representation is proposed, addressing the need for superordinate and basic-level categorization and for the identification of specific instances of familiar categories.
IEEE Transactions on Pattern Analysis and Machine IntelligenceModel-Based Three-Dimensional Interpretations of Two-Dimensional Images
359 Citations1983Rodney A. Brooks
Neural ComputationSEEMORE: Combining Color, Shape, and Texture Histogramming in a Neurally Inspired Approach to Visual Object Recognition
344 Citations1997Bartlett W. Mel
It is concluded that in the light of the vast hardware resources available in the ventral stream of the primate visual system relative to those exercised here, the appealingly simple feature-space conjecture remains worthy of serious consideration as a neurobiological model.
Cerebral CortexHow Are Three-Dimensional Objects Represented in the Brain?
304 Citations1995HH Bülthoff, Shimon Edelman +1 more
In a variety of psychophysical experiments that explore different aspects of the problem of object recognition and representation in human vision, models based on multiple-views representations replicated many of the psychophysical results concerning the observed pattern of human performance.
General Pattern Theory
284 Citations1994Ulf Grenander
IEEE Transactions on Pattern Analysis and Machine IntelligenceAlgebraic functions for recognition
265 Citations1995Amnon Shashua
The trilinearity result is shown to be of much practical use in visual recognition by alignment-yielding a direct reprojection method that cuts through the computations of camera transformation, scene structure and epipolar geometry.
Cerebral CortexSequence Seeking and Counter Streams: A Computational Model for Bidirectional Information Flow in the Visual Cortex
263 Citations1995Shimon Ullman
A computational model is proposed for some general aspects of information flow in the visual cortex that serves to account for known aspects of cortical interconnections and to derive new predictions.
Lecture notes in computer scienceObject recognition using multidimensional receptive field histograms
238 Citations1996Bernt Schiele, James L. Crowley
The mathematical foundations of the technique are described and the results of experiments which compare robustness and recognition rates for different local neighborhood operators and histogram similarity measurements are presented.
Probabilistic object recognition using multidimensional receptive field histograms
189 Citations1996Bernt Schiele, James L. Crowley
The method for histogram matching is extended to compute the probability of the presence of an object in an image and shows that receptive field histograms provide a technique for object recognition which is robust, has low computational cost and a computational complexity which is linear with the number of pixels.
Journal of Experimental Psychology Human Perception & PerformanceViewpoint-dependent mechanisms in visual object recognition: Reply to Tarr and Bülthoff (1995).
186 Citations1995Irving Biederman, Peter Gerhardstein
Minds and MachinesRepresentation, similarity, and the chorus of prototypes
164 Citations1995Shimon Edelman
The present preliminary study appears to indicate that this concept of representation is computationally viable, and is compatible with psychological and neurobiological data.
Neuronal architectures for pattern-theoretic problems.
147 Citations1994David Mumford
Compositionality, MDL Priors, and Object Recognition
115 Citations1996Elie Bienenstock, Stuart Geman +1 more
A compositional model is proposed in which primitives are recursively composed, subject to syntactic restrictions, to form tree-structured objects and object groupings for global vision models such as deformable templates.
Philosophical Transactions of the Royal Society B Biological SciencesA model of visual recognition and categorization
112 Citations1997Shimon Edelman, Sharon Duvdevani-Bar
The resulting representational scheme based on similarities to prototypes appears to be computationally viable, and is readily mapped onto the mechanisms of biological vision revealed by recent psychophysical and physiological studies.
MPG.PuRe (Max Planck Society)How are three-dimensional objects represented in the brain?
112 Citations1994HH Bülthoff
The Psychology of learning and motivation/The psychology of learning and motivationLearning as Extraction of Low-Dimensional Representations
66 Citations1997Shimon Edelman, Nathan Intrator
This chapter discusses that the effectiveness of living representational systems suggest that there must be something special about such systems that allows them to harbor representations of the world, and suggests that the possibility of effective representation stems from theLow-dimensional nature of the real-world classification tasks: an intelligent system would do well merely by reflecting the low-dimensional distal space internally.
International Journal of Computer VisionRecognition Using Region Correspondences
56 Citations1997Ronen Basri, David W. Jacobs
The new approach combines many of the advantages of the previous two approaches, while avoiding some of their pitfalls, and makes use of region information that reflects the true shape of the object.
Cambridge University Press eBooksPriors, preferences and categorical percepts
44 Citations1996Whitman Richards, Allan Jepson +1 more
The aim is to understand why the image structures in the upper panel support the assertion that they must arise only from very particular world structures, whereas the lower two structures seem more ambiguous.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe Recovery of Three-Dimensional Structure from Image Curves
44 Citations1985David Lowe, Thomas O. Binford
A class of inferences is described which allows the recovery of three-dimensional structures from the two-dimensional curves in an image and it can be shown that many potential interpretations of image curves are highly improbable.
International Journal of Computer VisionRecognition by prototypes
41 Citations1996Ronen Basri
The paper concludes with an algorithm for constructing optimal prototypes for classes of objects, which combines the correspondence and object pose computed in the categorization stage to align the prototype with the image with the result that identification is reduced to a series of simple template comparisons.
Neural ComputationSimilarity, Connectionism, and the Problem of Representation in Vision
40 Citations1997Shimon Edelman, Sharon Duvdevani-Bar
The computational requirements of representation that preserves similarity ranks are discussed and the relative straightforwardness of its connectionist implementation is pointed out.
Recognition using region correspondences
28 Citations2002Ronen Basri, David Jacobs
DSpace@MIT (Massachusetts Institute of Technology)Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects
28 Citations1985Jonathan H. Connell
An implemented system for learning structural prototypes from gray-scale images and a learning algorithm that forms class models from the descriptions produced and used these models to recognize new members of the class is exhibited.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe space requirements of indexing under perspective projections
21 Citations1996David W. Jacobs
It is shown that in this case, one must use a 3D surface to represent model groups, and an analytic description of such a surface is provided, in contrast to the cases of scaled-orthographic or affine projection.
CogPrints (Cogprints)Learning Low Dimensional Representations of Visual Objects With Extensive Use of Prior Knowledge
14 Citations1997Nathan Intrator, Shimon Edelman
A series of computational experiments involving parameterized fractal images and real human faces indicate that the low-dimensional representation extracted by the method leads to improved generalization in the learned tasks, and is likely to preserve the topology of the original space.
MPG.PuRe (Max Planck Society)Neural Models for Part-Whole Hierarchies
13 Citations1996Maximilian Riesenhuber, Peter Dayan
A connectionist method for representing images that explicitly addresses their hierarchical nature is presented, combining data from neuroscience about whole-object viewpoint sensitive cells in inferotemporal cortex and attentional basis-field modulation in V4 with ideas about hierarchical descriptions based on microfeatures.
Network Computation in Neural SystemsLearning low-dimensional representations via the usage of multiple-class labels
11 Citations1997Nathan Intrator, Shimon Edelman
The International Journal of Supercomputing ApplicationsSeeing in Parallel: the Vision Machine
10 Citations1988James J. Little, Tomaso Poggio +1 more
The integration stage, based on coupled Markov random field models, leads to a cartoon-like map of the discontinuities in the scene, with partial labeling of the brightness edges in terms of their physical origin.
A pictorial approach to object classification
9 Citations1991Yerucham Shapira, Shimon Ullman
This work extends previous alignment schemes in two main directions: extending the set of allowed transformations between the model and the viewed object, and using structural aspects of the internal models, namely, their part decomposition.
CogPrints (Cogprints)Biological Constraints and the Representation of Structure in Vision and Language
8 Citations1994Shimon Edelman
The model of script understanding introduced in the target book appears promising, both because it treats seriously the question of architecture of the language processor, and because its architectural features resemble those used in modeling other cognitive modalities such as vision.
Visual Processing in the Temporal Lobe for Invariant Object Recognition
5 Citations1996Edmund T. Rolls
Evidence is drawn together on how information about visual stimuli is represented in the temporal cortical visual areas and the brain areas to which these are connected; on how these representations are formed; and on how learning about these representations occurs.
eScholarship (California Digital Library)MetriCat: A Representation for Basic and Subordinate-level Classification
1 Citations1996Stankiewicz, Brian J., Hummel, John E.