Neural mechanisms of object recognition
Current Opinion in NeurobiologyPublished 1 April 2002
Maximilian Riesenhuber, Tomaso Poggio
Citations379
SJR quartileQ1
SJR score2.54
SNIP1.27
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
A putative model of object recognition in cortex is proposed, spanning issues regarding invariance, selectivity, representation and levels of recognition, based on single-unit recordings from behaving monkeys and human functional magnetic resonance imaging studies.
Abstract
Single-unit recordings from behaving monkeys and human functional magnetic resonance imaging studies have continued to provide a host of experimental data on the properties and mechanisms of object recognition in cortex. Recent advances in object recognition, spanning issues regarding invariance, selectivity, representation and levels of recognition have allowed us to propose a putative model of object recognition in cortex.
Keywords
Neuroscience
Journal of NeuroscienceThe Fusiform Face Area: A Module in Human Extrastriate Cortex Specialized for Face Perception
7,943 Citations1997Nancy Kanwisher, Josh H. McDermott +1 more
The data allow us to reject alternative accounts of the function of the fusiform face area (area “FF”) that appeal to visual attention, subordinate-level classification, or general processing of any animate or human forms, demonstrating that this region is selectively involved in the perception of faces.
NatureNeurophysiological investigation of the basis of the fMRI signal
6,458 Citations2001Nikos K. Logothetis, J Pauls +3 more
These findings suggest that the BOLD contrast mechanism reflects the input and intracortical processing of a given area rather than its spiking output, and that LFPs yield a better estimate of BOLD responses than the multi-unit responses.
A morphable model for the synthesis of 3D faces
4,799 Citations1999Volker Blanz, Thomas Vetter
A new technique for modeling textured 3D faces by transforming the shape and texture of the examples into a vector space representation, which regulates the naturalness of modeled faces avoiding faces with an "unlikely" appearance.
ScienceDistributed and Overlapping Representations of Faces and Objects in Ventral Temporal Cortex
4,144 Citations2001James V. Haxby, M. Ida Gobbini +4 more
The functional architecture of the object vision pathway in the human brain was investigated using functional magnetic resonance imaging to measure patterns of response in ventral temporal cortex while subjects viewed faces, cats, five categories of man-made objects, and nonsense pictures, and a distinct pattern of response was found for each stimulus category.
Nature NeuroscienceHierarchical models of object recognition in cortex
3,404 Citations1999Maximilian Riesenhuber, Tomaso Poggio
A new hierarchical model consistent with physiological data from inferotemporal cortex that accounts for this complex visual task and makes testable predictions is described.
NatureA cortical representation of the local visual environment
3,112 Citations1998Russell A. Epstein, Nancy Kanwisher
Evidence is presented that a particular area within human parahippocampal cortex is involved in a critical component of navigation: perceiving the local visual environment, and it is proposed that the PPA represents places by encoding the geometry of the local environment.
ScienceA Cortical Area Selective for Visual Processing of the Human Body
2,113 Citations2001Paul E. Downing, Yuhong Jiang +2 more
A series of functional magnetic resonance imaging studies revealing substantial evidence for a distinct cortical region in humans that responds selectively to images of the human body, as compared with a wide range of control stimuli.
Proceedings of the National Academy of SciencesObject-related activity revealed by functional magnetic resonance imaging in human occipital cortex.
1,818 Citations1995Rafael Malach, J.B. Reppas +8 more
Evidence for an intermediate link in the chain of processing stages leading to object recognition in human visual cortex is reported, which suggests that the enhanced responses to objects were not a manifestation of low-level visual processing.
Journal of NeurophysiologyVisual properties of neurons in inferotemporal cortex of the Macaque.
1,501 Citations1972Charles G. Gross, Carlos Eduardo Rocha‐Miranda +1 more
There are several lines of evidence suggesting that a possible site for further processing of visual information and perhaps even for storage of such information might, in the monkey, be inferotemporal cortexthe cortex on the inferior convexity of the temporal lobe.
Vision ResearchThe lateral occipital complex and its role in object recognition
1,482 Citations2001Kalanit Grill‐Spector, Zoe Kourtzi +1 more
Overall, these results indicate that the lateral occipital complex plays an important role in human object recognition.
Journal of NeuroscienceStimulus-selective properties of inferior temporal neurons in the macaque
1,449 Citations1984Robert Desimone, TD Albright +2 more
The first systematic survey of the responses of IT neurons to both simple stimuli and highly complex stimuli indicates that there may be specialized mechanisms for the analysis of faces in IT cortex.
Nature NeuroscienceExpertise for cars and birds recruits brain areas involved in face recognition
1,427 Citations2000L. Gauthier, Pawel Skudlarski +2 more
It is suggested that level of categorization and expertise, rather than superficial properties of objects, determine the specialization of the FFA.
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.
Nature NeuroscienceActivation of the middle fusiform 'face area' increases with expertise in recognizing novel objects
1,205 Citations1999L. Gauthier, Michael J. Tarr +3 more
Functional magnetic resonance imaging was used to measure changes associated with increasing expertise in brain areas selected for their face preference, and evidence is presented that expertise recruits the fusiform gyrus 'face area'.
ScienceCategorical Representation of Visual Stimuli in the Primate Prefrontal Cortex
1,155 Citations2001David J. Freedman, Maximilian Riesenhuber +2 more
Current BiologyShape representation in the inferior temporal cortex of monkeys
980 Citations1995Nikos K. Logothetis, J Pauls +1 more
The results suggest that IT neurons can develop a complex receptive field organization as a consequence of extensive training in the discrimination and recognition of objects, and support the idea that a population of neurons tuned to a different object aspect, and each showing a certain degree of invariance to image transformations--may encode at least some types of complex three-dimensional objects.
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.
Philosophical Transactions of the Royal Society B Biological SciencesOrganization and functions of cells responsive to faces in the temporal cortex
893 Citations1992David I. Perrett, Jari K. Hietanen +2 more
The selectivity for view suggests that the neural operations underlying face or head recognition rely on parallel analyses of different characteristic views of the head, the outputs of these view-specific analyses being subsequently combined to support view-independent (object-centred) recognition.
Nature NeurosciencePrototype-referenced shape encoding revealed by high-level aftereffects
889 Citations2001David A. Leopold, Alice J. O’Toole +2 more
It is found that exposure to an individual face for a few seconds generated a significant and precise bias in the subsequent perception of face identity, suggesting that the encoding of faces and other complex patterns draws upon contrastive neural mechanisms that reference the central tendency of the stimulus category.
Journal of NeurophysiologyNeuronal selectivities to complex object features in the ventral visual pathway of the macaque cerebral cortex
832 Citations1994Eiry Kobatake, Keiji Tanaka
It is suggested that local neuronal networks in V4 and posterior IT play an essential role in the formation of selective responses to complex object features.
Journal of Experimental Psychology GeneralObjects, parts, and categories.
738 Citations1984Barbara Tversky, Kathleen Hemenway
Journal of NeuroscienceCoding of Border Ownership in Monkey Visual Cortex
724 Citations2000Hong Zhou, Howard Steven Friedman +1 more
The short latencies and incomplete cue invariance suggest that the border-ownership effect is generated within the visual cortex rather than projected down from higher levels.
Journal of NeurophysiologyVisual properties of neurons in area V4 of the macaque: sensitivity to stimulus form
699 Citations1987Robert Desimone, Stan Schein
The large majority of V4 cells were tuned to the length and width of bars, and the "shape" of the optimal bar varied from cell to cell, as has been reported for cells in the dorsolateral visual area of the owl monkey.
Nature NeuroscienceModels of object recognition
664 Citations2000Maximilian Riesenhuber, Tomaso Poggio
This work briefly review some recent trends in computational vision and then focuses on feedforward, view-based models that are supported by psychophysical and physiological data.
Nature NeuroscienceFFA: a flexible fusiform area for subordinate-level visual processing automatized by expertise
652 Citations2000M. J. Tarr, L. Gauthier
It is concluded that the apparent face selectivity of the fusiform face area reflects a more generalized form of processing not intrinsically specific to faces.
NatureColumns for visual features of objects in monkey inferotemporal cortex
637 Citations1992Ichiro Fujita, Keiji Tanaka +2 more
The anterior inferotemporal area of the monkey cortex, the final station of the visual cortical stream crucial for object recognition, consists of columns, each containing cells responsive to similar visual features of objects.
ScienceSparse Population Coding of Faces in the Inferotemporal Cortex
599 Citations1992Malcolm P. Young, Shigeru Yamane
Population analysis of cells in the temporal cortex of monkeys showed that information is carried at the level of the population and that representations of complex stimuli in the higher visual areas may take the form of a sparse population code.
Journal of Cognitive NeuroscienceFace-Selective Cells in the Temporal Cortex of Monkeys
568 Citations1991Robert Desimone
A critical analysis of the evidence for face neurons is presented and the implications of these neurons for models of object recognition are discussed and some analogies with the development of language in humans are suggested.
Journal of NeurophysiologyResponses to Contour Features in Macaque Area V4
553 Citations1999Anitha Pasupathy, Charles E. Connor
The results suggest that V4 processes information about contour features as a step toward complex shape recognition, and a strong bias toward convex features implies a neural basis for the well-known perceptual dominance of convexity.
Progress in NeurobiologyINVARIANT FACE AND OBJECT RECOGNITION IN THE VISUAL SYSTEM
543 Citations1997Guy Wallis, Edmund T. Rolls
Evidence is described, showing that some neurons in the macaque temporal cortical visual areas have responses that are invariant with respect to the position, size and view of faces and objects, and that these neurons show rapid processing and rapid learning.
ScienceNeuronal Mechanisms of Object Recognition
522 Citations1993Keiji Tanaka
Recent experimental findings about the representation of object images in the inferotemporal cortex, a brain structure that is thought to be essential for object vision, are summarized and discussed in relation to the computational frames proposed for object recognition.
Cerebral CortexView-invariant representations of familiar objects by neurons in the inferior temporal visual cortex
462 Citations1998Martin J. Booth
A population of single neurons in the temporal visual cortex that have view-invariant representations of familiar objects are described, and the coding scheme was shown to be sparse distributed, with relatively independent information being provided by the different neurons.
Journal of NeurophysiologyNeural responses to polar, hyperbolic, and Cartesian gratings in area V4 of the macaque monkey
454 Citations1996Jack L. Gallant, Charles E. Connor +3 more
The responses of 103 neurons in visual area V4 of anesthetized macaque monkeys to two novel classes of visual stimuli, polar and hyperbolic sinusoidal gratings, were studied to identify cells that had orderly tuning profiles in the various stimulus spaces.
Nature NeuroscienceComplex objects are represented in macaque inferotemporal cortex by the combination of feature columns
370 Citations2001Kazushige Tsunoda, Y. Yamane +2 more
Intrinsic signal imaging from inferotemporal cortex revealed that visually presented objects activated patches in a distributed manner, suggesting that an object is represented by a combination of cortical columns, each of which represents a visual feature (feature column).
Journal of NeurophysiologyEffects of Shape-Discrimination Training on the Selectivity of Inferotemporal Cells in Adult Monkeys
334 Citations1998Eucaly Kobatake, Gang Wang +1 more
Journal of NeuroscienceSelectivity for Complex Shapes in Primate Visual Area V2
329 Citations2000Jay Hegdé, David C. Van Essen
The results indicate that V2 cells explicitly represent complex shape information and suggest specific types of higher order visual information that V1 cells extract from visual scenes.
ScienceOptical Imaging of Functional Organization in the Monkey Inferotemporal Cortex
305 Citations1996Gang Wang, Keiji Tanaka +1 more
To investigate the functional organization of object recognition, the technique of optical imaging was applied to the primate inferotemporal cortex, which is thought to be essential for object recognition.
Journal of NeuroscienceNoticing Familiar Objects in Real World Scenes: The Role of Temporal Cortical Neurons in Natural Vision
244 Citations2001David L. Sheinberg, Nikos K. Logothetis
A group of visual neurons that exhibited stimulus-selective neuronal bursts just before the monkey's response suggests that they contribute to the process of noticing familiar objects in the real world.
Current Opinion in NeurobiologyMechanisms of visual object recognition: monkey and human studies
222 Citations1997Keiji Tanaka
The human homologue of the monkey inferotemporal cortex has been identified through use of new non-invasive techniques and the close correlation between the activity of inference cells and the perception of object images has been revealed.
Journal of Experimental Psychology Learning Memory and CognitionCategory differentiation in object recognition: Typicality constraints on the basic category advantage.
214 Citations1985Gregory L. Murphy, Hiram Brownell
It is argued that atypical subordinate categories are highly differentiated and should be responded to as fast as basic categories in object recognition, and the results supported this view and ruled out the hypothesis that objects are necessarily identified as members of basic categories before further identification.
Image and Vision ComputingNeurophysiology of shape processing
213 Citations1993David I. Perrett, Mike W. Oram
This scheme provides a route to 3D object recognition through 2D shape description and reduces the problem of perceptual invariance to a series of independent analyses with an associative link established between the outputs.
NeuronAre Cortical Models Really Bound by the “Binding Problem”?
197 Citations1999Maximilian Riesenhuber, Tomaso Poggio
European Journal of NeuroscienceCategorization of complex visual images by rhesus monkeys. Part 2: single‐cell study
175 Citations1999Rufin Vogels
A strong within‐category selectivity challenges the idea that a prototype is represented at the single neuron level, but suggests that ordinate‐level categorization is based on a population of neurons, each selective for a limited set of exemplars.
Cognitive NeuropsychologyIS FACE RECOGNITION NOT SO UNIQUE AFTER ALL?
130 Citations2000L. Gauthier, Nikos K. Logothetis
Some new evidence in the monkey is discussed suggesting that any arbitrary homogeneous class of artificial objects—which the animal has to individually learn, remember, and recognise again and again from among a large number of distractors sharing a number of common features with the target—can induce configurational selectivity in the response of neurons in the visual system.
Nature NeuroscienceShape-coding in IT cells generalizes over contrast and mirror reversal, but not figure-ground reversal
118 Citations2001Gordon C. Baylis, Jon Driver
These results imply that neurons in inferior temporal cortex respond to components of visual shape derived only after figure–ground assignment of contours, not to the contours themselves.
Nature NeuroscienceForm representation in monkey inferotemporal cortex is virtually unaltered by free viewing
108 Citations2000James J. DiCarlo, John H. R. Maunsell
By making small, real-time stimulus adjustments, this work produces nearly identically retinal stimulation during controlled and free viewing, which indicates neuronal representations that likely underlie form recognition are virtually unaltered by free viewing.
Experimental Brain ResearchResponsiveness of inferotemporal single units to visual pattern stimuli in monkeys performing discrimination
100 Citations1980Takayuki Sato, Tetsuya Kawamura +1 more
The activity of most units responsive to two or three patterns was dependent on pattern shapes rather than the learnt meaning of the patterns, and unresponsiveness to components of the response-eliciting patterns was indicated in some of these units.
NeuronPrediction of Orientation Selectivity from Receptive Field Architecture in Simple Cells of Cat Visual Cortex
83 Citations2001Ilan Lampl, Jeffrey S. Anderson +2 more
The results show that the spatial organization of the receptive field can account for a large fraction of the orientation selectivity of simple cells.
Cerebral CortexResponses of macaque inferior temporal neurons to overlapping shapes
50 Citations1997Marcus Missal
It is found that the response and selectivity of TE neurons to the figure can be dramatically altered, most commonly reduced, when the figure is overlapping the background, and this reduction was also present when the monkey was required to actively discriminate the figures from varying backgrounds during recording.
Experimental Brain ResearchThe effects of lighting conditions on responses of cells selective for face views in the macaque temporal cortex
50 Citations1992Jari K. Hietanen, David I. Perrett +3 more
The results indicate that constancy of recognition across different lighting conditions is apparent in the responses of single cells in the temporal cortex, and lighting constancy appears to be established by matching the retinal image to view-specific descriptions of objects.
Computational Models of Object Recognition in Cortex: A Review
48 Citations2000Maximilian Riesenhuber, Tomaso Poggio
The focus of the review is on feedforward, view-based models that are supported by psychophysical and physiological data and represent different trade-offs between specificity and invariance.
DSpace@MIT (Massachusetts Institute of Technology)A Note on Object Class Representation and Categorical Perception
21 Citations1999Maximilian Riesenhuber, Tomaso Poggio
DSpace@MIT (Massachusetts Institute of Technology)The Individual is Nothing, the Class Everything: Psychophysics and Modeling of Recognition in Obect Classes
13 Citations2000Maximilian Riesenhuber, Tomaso Poggio
Experimental evidence is found, supported by modeling results, that training builds a viewpointand class-specific representation that supplements a pre-existing representation with lower shape discriminability but possibly greater viewpoint invariance.