Generalization between canonical and non-canonical views in object recognition.

Viewpoint generalization in object recognition is the process that allows recognition of a given 3D object from many different viewpoints despite variations in its 2D projections. We used the canonical view effects as a foundation to empirically test the validity of a major theory in object recognition, the view-approximation model (Poggio & Edelman, 1990). This model predicts that generalization should be better when an object is first seen from a non-canonical view and then a canonical view than when seen in the reversed order. We also manipulated object similarity to study the degree to which this view generalization was constrained by shape details and task instructions (object vs. image recognition). Old-new recognition performance for basic and subordinate level objects was measured in separate blocks. We found that for object recognition, view generalization between canonical and non-canonical views was comparable for basic level objects. For subordinate level objects, recognition performance was more accurate from non-canonical to canonical views than the other way around. When the task was changed from object recognition to image recognition, the pattern of the results reversed. Interestingly, participants responded "old" to "new" images of "old" objects with a substantially higher rate than to "new" objects, despite instructions to the contrary, thereby indicating involuntary view generalization. Our empirical findings are incompatible with the prediction of the view-approximation theory, and argue against the hypothesis that views are stored independently.

[1]  W. Hayward.  After the viewpoint debate: where next in object recognition? , 2003, Trends in Cognitive Sciences.

[2]  M J Tarr,et al.  Is human object recognition better described by geon structural descriptions or by multiple views? Comment on Biederman and Gerhardstein (1993). , 1995, Journal of experimental psychology. Human perception and performance.

[3]  J. Koenderink,et al.  The singularities of the visual mapping , 1976, Biological Cybernetics.

[4]  H. Christopher Longuet-Higgins,et al.  Recognizing three dimensions , 1990, Nature.

[5]  Z Liu.  Viewpoint dependency in object representation and recognition. , 1996, Spatial vision.

[6]  A. Yuille,et al.  Object perception as Bayesian inference. , 2004, Annual review of psychology.

[7]  Heinrich H Bülthoff,et al.  Image-based object recognition in man, monkey and machine , 1998, Cognition.

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

[9]  Refractor.  Vision , 2000, The Lancet.

[10]  S. Edelman,et al.  Canonical views in object representation and recognition , 1994, Vision Research.

[11]  Isabel Gauthier,et al.  Three-dimensional object recognition is viewpoint dependent , 1998, Nature Neuroscience.

[12]  Daniel Kersten,et al.  Bayesian models of object perception , 2003, Current Opinion in Neurobiology.

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

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

[15]  A. Taylor,et al.  The contribution of the right parietal lobe to object recognition. , 1973, Cortex; a journal devoted to the study of the nervous system and behavior.

[16]  Ulf Grenander,et al.  General Pattern Theory: A Mathematical Study of Regular Structures , 1993 .

[17]  David W. Jacobs,et al.  Uncertainty Propagation in Model-Based Recognition , 1998, International Journal of Computer Vision.

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

[19]  I. Gauthier,et al.  Visual object understanding , 2004, Nature Reviews Neuroscience.

[20]  Shimon Edelman,et al.  Renewing the respect for similarity , 2012, Front. Comput. Neurosci..

[21]  D G Pelli,et al.  The VideoToolbox software for visual psychophysics: transforming numbers into movies. , 1997, Spatial vision.

[22]  Pablo Gomez,et al.  Memory for objects in canonical and noncanonical viewpoints , 2008, Psychonomic bulletin & review.

[23]  Irving Biederman,et al.  Viewpoint-Dependent Mechanisms in Visual Object Recognition : Reply to Tarr and Biilthoff ( 1995 ) , 2004 .

[24]  K Verfaillie,et al.  A corpus of 714 full-color images of depth-rotated objects , 1995, Perception & psychophysics.

[25]  I. Biederman,et al.  Recognizing depth-rotated objects: Evidence and conditions for three-dimensional viewpoint invariance. , 1993 .

[26]  E. Rolls.  High-level vision: Object recognition and visual cognition, Shimon Ullman. MIT Press, Bradford (1996), ISBN 0 262 21013 4 , 1997 .

[27]  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.

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

[29]  W. Richards,et al.  Perception as Bayesian Inference , 2008 .

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

[31]  M. Harries,et al.  Preferential Inspection of Views of 3-D Model Heads , 1991, Perception.

[32]  David L. Sheinberg,et al.  Visual object recognition. , 1996, Annual review of neuroscience.

[33]  Shimon Edelman,et al.  Bringing the Grandmother back into the Picture: A Memory-Based View of Object Recognition , 1990, Int. J. Pattern Recognit. Artif. Intell..

[34]  H H Bülthoff,et al.  How are three-dimensional objects represented in the brain? , 1994, Cerebral cortex.

[35]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

[36]  Antonio Torralba,et al.  Sharing Visual Features for Multiclass and Multiview Object Detection , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  M J Tarr,et al.  What Object Attributes Determine Canonical Views? , 1999, Perception.

[38]  Michael Werman,et al.  On View Likelihood and Stability , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[39]  Guy Wallis,et al.  The prototype effect revisited: Evidence for an abstract feature model of face recognition. , 2008, Journal of vision.

[40]  I. Biederman.  Recognizing depth-rotated objects: a review of recent research and theory. , 2000, Spatial vision.

[41]  M. Tarr,et al.  Mental rotation and orientation-dependence in shape recognition , 1989, Cognitive Psychology.

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

[43]  Gordon E. Legge,et al.  The viewpoint complexity of an object-recognition task , 1998, Vision Research.

[44]  David C. Knill,et al.  Object classification for human and ideal observers , 1995, Vision Research.

[45]  M. Harries,et al.  Use of Preferential Inspection to Define the Viewing Sphere and Characteristic Views of an Arbitrary Machined Tool Part , 1992, Perception.

[46]  Tomaso Poggio,et al.  Models of object recognition , 2000, Nature Neuroscience.

[47]  S. Edelman,et al.  Orientation dependence in the recognition of familiar and novel views of three-dimensional objects , 1992, Vision Research.

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

[49]  D I Perrett,et al.  Characteristic Views and the Visual Inspection of Simple Faceted and Smooth Objects: ‘Tetrahedra and Potatoes’ , 1988, Perception.

[50]  S. Ullman.  Object recognition and segmentation by a fragment-based hierarchy , 2007, Trends in Cognitive Sciences.

[51]  H. Bülthoff,et al.  Viewpoint Dependence in Visual and Haptic Object Recognition , 2001, Psychological science.

[52]  Michael J. Tarr.  Is human object recognition better described by geon structural description or by multiple views , 1995 .

[53]  D H Brainard,et al.  The Psychophysics Toolbox. , 1997, Spatial vision.

[54]  H. Bülthoff,et al.  Effects of temporal association on recognition memory , 2001, Proceedings of the National Academy of Sciences of the United States of America.