The Role of Surface-Based Representations of Shape in Visual Object Recognition

This study contrasted the role of surfaces and volumetric shape primitives in three-dimensional object recognition. Observers (N = 50) matched subsets of closed contour fragments, surfaces, or volumetric parts to whole novel objects during a whole–part matching task. Three factors were further manipulated: part viewpoint (either same or different between component parts and whole objects), surface occlusion (comparison parts contained either visible surfaces only, or a surface that was fully or partially occluded in the whole object), and target–distractor similarity. Similarity was varied in terms of systematic variation in nonaccidental (NAP) or metric (MP) properties of individual parts. Analysis of sensitivity (d′) showed a whole–part matching advantage for surface-based parts and volumes over closed contour fragments—but no benefit for volumetric parts over surfaces. We also found a performance cost in matching volumetric parts to wholes when the volumes showed surfaces that were occluded in the whole object. The same pattern was found for both same and different viewpoints, and regardless of target–distractor similarity. These findings challenge models in which recognition is mediated by volumetric part-based shape representations. Instead, we argue that the results are consistent with a surface-based model of high-level shape representation for recognition.

[1]  M. Tarr,et al.  Testing conditions for viewpoint invariance in object recognition. , 1997, Journal of experimental psychology. Human perception and performance.

[2]  Shinsuke Shimojo,et al.  Visual surface representation: a critical link between lower-level and higher level vision , 1995 .

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

[4]  J T Todd,et al.  The Discriminability of Local Surface Structure , 1996, Perception.

[5]  J Palmer,et al.  Memory for objects and parts , 1991, Perception & psychophysics.

[6]  E. C. Leek,et al.  Inhibition of return for objects and locations in static displays , 2003, Perception & psychophysics.

[7]  S. Ullman.  Three-dimensional object recognition based on the combination of views , 1998, Cognition.

[8]  Irene Reppa,et al.  Surface but not volumetric part structure mediates three-dimensional shape representation: Evidence from part–whole priming , 2009, Quarterly journal of experimental psychology.

[9]  I. Biederman,et al.  Size invariance in visual object priming , 1992 .

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

[11]  Lina I. Conlan,et al.  Eye movement patterns during the recognition of three-dimensional objects: preferential fixation of concave surface curvature minima. , 2012, Journal of vision.

[12]  J. Andrade-Cetto.  Object Recognition , 2003 .

[13]  J. Hummel,et al.  An architecture for rapid, hierarchical structural description , 1996 .

[14]  Lina I. Davitt,et al.  Implicit encoding of extrinsic object properties in stored representations mediating recognition: Evidence from shadow-specific repetition priming , 2015, Vision Research.

[15]  Irene Reppa,et al.  The structure of three-dimensional object representations in human vision: evidence from whole-part matching. , 2005, Journal of experimental psychology. Human perception and performance.

[16]  Paul E. Dux,et al.  Orientation Sensitivity at Different Stages of Object Processing: Evidence from Repetition Priming and Naming , 2008, PloS one.

[17]  Lina I. Davitt,et al.  Shape Information Mediating Basic- and Subordinate-Level Object Recognition Revealed by Analyses of Eye Movements , 2013, Journal of experimental psychology. Human perception and performance.

[18]  Irving Biederman,et al.  Sensitivity to nonaccidental properties across various shape dimensions , 2012, Vision Research.

[19]  J. Todd,et al.  Perceptual representation of visible surfaces , 2003, Perception & psychophysics.

[20]  Carole Parron,et al.  Contrasting the edge- and surface-based theories of object recognition: behavioral evidence from macaques (Macaca mulatta). , 2010, Journal of experimental psychology. Animal behavior processes.

[21]  R. Rosenfeld.  Nature , 2009, Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery.

[22]  Robert B. Fisher.  From Surfaces to Objects: Computer Vision and Three Dimensional Scene Analysis , 1989 .

[23]  I. Biederman,et al.  Priming contour-deleted images: Evidence for intermediate representations in visual object recognition , 1991, Cognitive Psychology.

[24]  Robert Bergevin,et al.  Generic Object Recognition: Building and Matching Coarse Descriptions from Line Drawings , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Irene Reppa,et al.  Successes and failures in producing attentional object-based cueing effects , 2011, Attention, Perception, & Psychophysics.

[26]  Zygmunt Pizlo,et al.  Symmetry, Shape, Surfaces, and Objects , 2011 .

[27]  Robert B. Fisher,et al.  Finding Surface Correspondance for Object Recognition and Registration Using Pairwise Geometric Histograms , 1998, ECCV.

[28]  Zygmunt Pizlo,et al.  3D Shape - Its Unique Place in Visual Perception , 2008 .

[29]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Lina I. Conlan,et al.  The Appearance of Shape in Visual Perception: Eye Movement Patterns During Recognition and Reaching , 2012 .

[31]  Shimon Edelman,et al.  Representation and recognition in vision , 1999 .

[32]  Franc Solina,et al.  Part-level object recognition using superquadrics , 2004, Comput. Vis. Image Underst..

[33]  Barr,et al.  Superquadrics and Angle-Preserving Transformations , 1981, IEEE Computer Graphics and Applications.

[34]  E. Leek.  The Analysis of Orientation-Dependent Time Costs in Visual Recognition , 1998, Perception.

[35]  Alex Pentland,et al.  Perceptual Organization and the Representation of Natural Form , 1986, Artif. Intell..

[36]  D. Foster,et al.  Recognizing novel three–dimensional objects by summing signals from parts and views , 2002, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[37]  M. Shishuku.  [Visual discrimination]. , 1974, Kokubyo Gakkai zasshi. The Journal of the Stomatological Society, Japan.

[38]  J. Paul Siebert,et al.  Local feature extraction and matching on range images: 2.5D SIFT , 2009, Comput. Vis. Image Underst..

[39]  Zygmunt Pizlo,et al.  New approach to the perception of 3D shape based on veridicality, complexity, symmetry and volume , 2010, Vision Research.

[40]  E. C. Leek,et al.  Effects of stimulus orientation on the identification of common polyoriented objects , 1998 .

[41]  Irving Biederman,et al.  One-shot viewpoint invariance in matching novel objects , 1999, Vision Research.

[42]  William G. Hayward,et al.  Stereo Disparity Facilitates View Generalization during Shape Recognition for Solid Multipart Objects , 2015, Quarterly journal of experimental psychology.

[43]  Ramakant Nevatia,et al.  Part-Based 3D Descriptions of Complex Objects from a Single Image , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[44]  I Biederman,et al.  Size Invariance in Visual Object Priming of Gray-Scale Images , 1995, Perception.

[45]  Michel Vidal-Naquet,et al.  Visual features of intermediate complexity and their use in classification , 2002, Nature Neuroscience.

[46]  Marlene Behrmann,et al.  Perceiving Parts and Shapes from Concave Surfaces , 2022 .

[47]  Jere Brophy.  Where Are the Data? A Reply to Confrey. , 1986 .

[48]  Stephen J. Johnston,et al.  A polarity effect in misoriented object recognition: The role of polar features in the computation of orientation-invariant shape representations , 2006 .

[49]  K Nakayama,et al.  Experiencing and perceiving visual surfaces. , 1992, Science.

[50]  H H Bülthoff,et al.  Psychophysical support for a two-dimensional view interpolation theory of object recognition. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[51]  J. Koenderink,et al.  Pictorial surface attitude and local depth comparisons , 1996, Perception & psychophysics.

[52]  Adolfo Guzmán-Arenas,et al.  Decomposition of a visual scene into three-dimensional bodies , 1968, AFIPS Fall Joint Computing Conference.

[53]  Hongjing Lu,et al.  Two forms of aftereffects induced by transparent motion reveal multilevel adaptation. , 2012, Journal of vision.

[54]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[55]  Martin Arguin,et al.  Orientation invariance in visual object priming depends on prime—target asynchrony , 2003, Perception & psychophysics.

[56]  Daphna Weinshall,et al.  A self-organizing multiple-view representation of 3D objects , 2004, Biological Cybernetics.

[57]  Guillaume Thierry,et al.  Computational mechanisms of object constancy for visual recognition revealed by event-related potentials , 2007, Vision Research.

[58]  Rae-Hong Park,et al.  A surface-based approach to 3-D object recognition using a mean field annealing neural network , 2002, Pattern Recognit..

[59]  James L. McClelland,et al.  Information integration in perception and communication , 1996 .

[60]  I. Biederman,et al.  Dynamic binding in a neural network for shape recognition. , 1992, Psychological review.

[61]  F. Attneave.  Some informational aspects of visual perception. , 1954, Psychological review.

[62]  Ramakant Nevatia,et al.  Recognizing 3-D Objects Using Surface Descriptions , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[63]  James T. Todd,et al.  The perception of surface orientation from multiple sources of optical information , 1995, Perception & psychophysics.

[64]  Sven J. Dickinson,et al.  Panel report: the potential of geons for generic 3-D object recognition , 1997, Image Vis. Comput..

[65]  G. Humphreys,et al.  The real-object advantage in agnosia: Evidence for a role of surface and depth information in object recognition , 2001, Cognitive Neuropsychology.

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

[67]  J Farley Norman,et al.  Stereoscopic shape discrimination is well preserved across changes in object size. , 2009, Acta psychologica.

[68]  Irene Reppa,et al.  Structure-Based Modulation of Inhibition of Return is Triggered by Object-Internal but not Occluding Shape Features , 2006, Quarterly journal of experimental psychology.

[69]  S. Grossberg,et al.  View-invariant object category learning, recognition, and search: How spatial and object attention are coordinated using surface-based attentional shrouds , 2009, Cognitive Psychology.

[70]  Hideko F. Norman,et al.  Visual discrimination of local surface structure: Slant, tilt, and curvedness , 2006, Vision Research.

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

[72]  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.

[73]  Alex M. Andrew,et al.  Object Recognition in Man, Monkey, and Machine , 2000 .

[74]  I. Biederman,et al.  Recognizing depth-rotated objects: evidence and conditions for three-dimensional viewpoint invariance. , 1993, Journal of experimental psychology. Human perception and performance.

[75]  Irene Reppa,et al.  The modulation of inhibition of return by objectinternal structure: Implications for theories of object-based attentional selection , 2003, Psychonomic bulletin & review.

[76]  I. Biederman.  In: An invitation to cognitive science , 2003 .

[77]  Julie M. Harris,et al.  Optimal integration of shading and binocular disparity for depth perception. , 2012, Journal of vision.

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