Object perception as Bayesian inference.

We perceive the shapes and material properties of objects quickly and reliably despite the complexity and objective ambiguities of natural images. Typical images are highly complex because they consist of many objects embedded in background clutter. Moreover, the image features of an object are extremely variable and ambiguous owing to the effects of projection, occlusion, background clutter, and illumination. The very success of everyday vision implies neural mechanisms, yet to be understood, that discount irrelevant information and organize ambiguous or noisy local image features into objects and surfaces. Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the task-dependent, probabilistic integration of prior object knowledge with image features.

[1]  D. Mackay.  The Epistemological Problem for Automata , 1956 .

[2]  H. Barlow,et al.  A method of determining the overall quantum efficiency of visual discriminations , 1962, The Journal of physiology.

[3]  D. M. Green,et al.  Signal detection theory and psychophysics , 1966 .

[4]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[5]  I. Rock.  The Logic of Perception , 1983 .

[6]  V. Ramachandran,et al.  The Neurobiology of Perception , 1985, Perception.

[7]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[8]  H H Bülthoff,et al.  Integration of depth modules: stereo and shading. , 1988, Journal of the Optical Society of America. A, Optics and image science.

[9]  J. Berger.  Statistical Decision Theory and Bayesian Analysis , 1988 .

[10]  Norberto M. Grzywacz,et al.  A computational theory for the perception of coherent visual motion , 1988, Nature.

[11]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[12]  H. Bülthoff,et al.  Does the brain know the physics of specular reflection? , 1990, Nature.

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

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

[15]  James J. Clark,et al.  Data Fusion for Sensory Information Processing Systems , 1990 .

[16]  D. Field,et al.  Human discrimination of fractal images. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[17]  G. Sperling,et al.  Object spatial frequencies, retinal spatial frequencies, noise, and the efficiency of letter discrimination , 1991, Vision Research.

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

[19]  D. Knill,et al.  Apparent surface curvature affects lightness perception , 1991, Nature.

[20]  Maggie Shiffrar,et al.  The influence of terminators on motion integration across space , 1992, Vision Research.

[21]  D Mumford,et al.  On the computational architecture of the neocortex. II. The role of cortico-cortical loops. , 1992, Biological cybernetics.

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

[23]  Edward H. Adelson,et al.  Recovering reflectance and illumination in a world of painted polyhedra , 1993, 1993 (4th) International Conference on Computer Vision.

[24]  V Bruce,et al.  Independent Effects of Lighting, Orientation, and Stereopsis on the Hollow-Face Illusion , 1993, Perception.

[25]  J. Frisby,et al.  Lightness Perception Can Be Affected by Surface Curvature from Stereopsis , 1994, Perception.

[26]  William T. Freeman,et al.  The generic viewpoint assumption in a framework for visual perception , 1994, Nature.

[27]  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.

[28]  Remo Guidieri.  Res , 1995, RES: Anthropology and Aesthetics.

[29]  Wendy L. Braje,et al.  Human efficiency for recognizing 3-D objects in luminance noise , 1995, Vision Research.

[30]  Geoffrey E. Hinton,et al.  The Helmholtz Machine , 1995, Neural Computation.

[31]  M. Landy,et al.  Measurement and modeling of depth cue combination: in defense of weak fusion , 1995, Vision Research.

[32]  D. G. Albrecht,et al.  Bayesian analysis of identification performance in monkey visual cortex: Nonlinear mechanisms and stimulus certainty , 1995, Vision Research.

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

[34]  A. Yuille,et al.  Bayesian decision theory and psychophysics , 1996 .

[35]  David C. Knill,et al.  Introduction: a Bayesian formulation of visual perception , 1996 .

[36]  Victor A. F. Lamme,et al.  Contextual Modulation in Primary Visual Cortex , 1996, The Journal of Neuroscience.

[37]  Paul A. Griffin,et al.  Statistical Approach to Shape from Shading: Reconstruction of Three-Dimensional Face Surfaces from Single Two-Dimensional Images , 1996, Neural Computation.

[38]  S. Ullman.  High-Level Vision: Object Recognition and Visual Cognition , 1996 .

[39]  T. Sanger,et al.  Probability density estimation for the interpretation of neural population codes. , 1996, Journal of neurophysiology.

[40]  Alan L. Yuille,et al.  Perception as Bayesian Inference: Introduction , 1996 .

[41]  U. Grenander.  Elements of Pattern Theory , 1996 .

[42]  Joseph S. Gati,et al.  Differences in perceived shape from shading correlate with activity in early visual areas , 1997, Current Biology.

[43]  Geoffrey E. Hinton,et al.  Generative models for discovering sparse distributed representations. , 1997, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[44]  Shree K. Nayar,et al.  Reflectance and texture of real-world surfaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[45]  Song-Chun Zhu,et al.  Prior Learning and Gibbs Reaction-Diffusion , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[46]  D H Brainard,et al.  Bayesian color constancy. , 1997, Journal of the Optical Society of America. A, Optics, image science, and vision.

[47]  Song-Chun Zhu,et al.  Minimax Entropy Principle and Its Application to Texture Modeling , 1997, Neural Computation.

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

[49]  Nikolaus F. Troje,et al.  Separation of texture and shape in images of faces for image coding and synthesis , 1997 .

[50]  Joshua B. Tenenbaum,et al.  Bayesian Modeling of Human Concept Learning , 1998, NIPS.

[51]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[52]  D. Perrett,et al.  The `Ideal Homunculus': decoding neural population signals , 1998, Trends in Neurosciences.

[53]  D. Knill,et al.  Discrimination of planar surface slant from texture: human and ideal observers compared , 1998, Vision Research.

[54]  P. Perona,et al.  Where is the sun? , 1998, Nature Neuroscience.

[55]  D. Knill,et al.  The perception of cast shadows , 1998, Trends in Cognitive Sciences.

[56]  William T. Freeman,et al.  Learning to Estimate Scenes from Images , 1998, NIPS.

[57]  Pascal Mamassian,et al.  Observer biases in the 3D interpretation of line drawings , 1998, Vision Research.

[58]  Paul E. Debevec,et al.  Rendering synthetic objects into real scenes: bridging traditional and image-based graphics with global illumination and high dynamic range photography , 1998, SIGGRAPH '08.

[59]  Zili Liu,et al.  2D observers for human 3D object recognition? , 1997, Vision Research.

[60]  A. Hurlbert,et al.  Perception of three-dimensional shape influences colour perception through mutual illumination , 1999, Nature.

[61]  Song-Chun Zhu,et al.  Embedding Gestalt Laws in Markov Random Fields , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[62]  Michael L. Platt,et al.  Neural correlates of decision variables in parietal cortex , 1999, Nature.

[63]  D Kersten,et al.  Viewpoint-Dependent Recognition of Familiar Faces , 1999, Perception.

[64]  Daniel Kersten,et al.  High-level Vision as Statistical Inference , 1999 .

[65]  Zili Liu,et al.  Dissociating stimulus information from internal representation—a case study in object recognition , 1999, Vision Research.

[66]  A. Borst.  Seeing smells: imaging olfactory learning in bees , 1999, Nature Neuroscience.

[67]  Yoav Freund,et al.  A Short Introduction to Boosting , 1999 .

[68]  William T. Freeman,et al.  Learning low-level vision , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[69]  Pietro Perona,et al.  Unsupervised Learning of Models for Recognition , 2000, ECCV.

[70]  R. Zemel,et al.  Information processing with population codes , 2000, Nature Reviews Neuroscience.

[71]  V. Lamme,et al.  The distinct modes of vision offered by feedforward and recurrent processing , 2000, Trends in Neurosciences.

[72]  M K Albert,et al.  The Generic Viewpoint Assumption and Bayesian Inference , 2000, Perception.

[73]  Bruno A. Olshausen,et al.  Vision and the Coding of Natural Images , 2000, American Scientist.

[74]  Alan L. Yuille,et al.  Probabilistic Motion Estimation Based on Temporal Coherence , 2000, Neural Computation.

[75]  Paul R. Schrater,et al.  Mechanisms of visual motion detection , 2000, Nature Neuroscience.

[76]  D. Tolhurst,et al.  The human visual system is optimised for processing the spatial information in natural visual images , 2000, Current Biology.

[77]  Tomaso A. Poggio,et al.  Regularization Networks and Support Vector Machines , 2000, Adv. Comput. Math..

[78]  Stephen H. Westin,et al.  Image-based bidirectional reflectance distribution function measurement. , 2000, Applied optics.

[79]  A. Oliva,et al.  Diagnostic Colors Mediate Scene Recognition , 2000, Cognitive Psychology.

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

[81]  J. Saunders,et al.  Perception of 3D surface orientation from skew symmetry , 2001, Vision Research.

[82]  M S Landy,et al.  Ideal cue combination for localizing texture-defined edges. , 2001, Journal of the Optical Society of America. A, Optics, image science, and vision.

[83]  A. O'Toole,et al.  Prototype-referenced shape encoding revealed by high-level aftereffects , 2001, Nature Neuroscience.

[84]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[85]  Paul A. Viola,et al.  Robust Real-time Object Detection , 2001 .

[86]  T. Hendler,et al.  A hierarchical axis of object processing stages in the human visual cortex. , 2001, Cerebral cortex.

[87]  Jeffrey S. Perry,et al.  Edge co-occurrence in natural images predicts contour grouping performance , 2001, Vision Research.

[88]  J T Todd,et al.  Ambiguity and the ‘Mental Eye’ in Pictorial Relief , 2001, Perception.

[89]  Pascal Mamassian,et al.  Interaction of visual prior constraints , 2001, Vision Research.

[90]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[91]  Edward H. Adelson,et al.  Statistics of real-world illumination , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[92]  J. Bullier.  Integrated model of visual processing , 2001, Brain Research Reviews.

[93]  H H Bülthoff,et al.  A Prior for Global Convexity in Local Shape-from-Shading , 2001, Perception.

[94]  Steve Marschner,et al.  A practical model for subsurface light transport , 2001, SIGGRAPH.

[95]  E H Adelson,et al.  Beyond Junctions: Nonlocal form Constraints on Motion Interpretation , 2001, Perception.

[96]  Paul R. Schrater,et al.  Vision, Psychophysics and Bayes , 2001 .

[97]  Z. Pizlo.  Perception viewed as an inverse problem , 2001, Vision Research.

[98]  Jacob feldman,et al.  Bayesian contour integration , 2001, Perception & psychophysics.

[99]  J. Tenenbaum,et al.  Generalization, similarity, and Bayesian inference. , 2001, The Behavioral and brain sciences.

[100]  Eero P. Simoncelli,et al.  Natural image statistics and neural representation. , 2001, Annual review of neuroscience.

[101]  N. Kanwisher,et al.  The lateral occipital complex and its role in object recognition , 2001, Vision Research.

[102]  Alan L. Yuille,et al.  The KGBR viewpoint-lighting ambiguity and its resolution by generic constraints , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[103]  T. Poggio,et al.  Neural mechanisms of object recognition , 2002, Current Opinion in Neurobiology.

[104]  Paul R. Schrater,et al.  Pattern inference theory: A probabilistic approach to vision , 2002 .

[105]  D. Kersten,et al.  Illusions, perception and Bayes , 2002, Nature Neuroscience.

[106]  Peter Dayan,et al.  Acetylcholine in cortical inference , 2002, Neural Networks.

[107]  M. Ernst,et al.  Humans integrate visual and haptic information in a statistically optimal fashion , 2002, Nature.

[108]  R. Jacobs.  What determines visual cue reliability? , 2002, Trends in Cognitive Sciences.

[109]  M. Landy,et al.  Bayesian Modelling of Visual Perception , 2002 .

[110]  Edward H. Adelson,et al.  Motion illusions as optimal percepts , 2002, Nature Neuroscience.

[111]  J. Elder,et al.  Ecological statistics of Gestalt laws for the perceptual organization of contours. , 2002, Journal of vision.

[112]  G. Legge,et al.  Mr. Chips 2002: new insights from an ideal-observer model of reading , 2002, Vision Research.

[113]  James M. Hillis,et al.  Combining Sensory Information: Mandatory Fusion Within, but Not Between, Senses , 2002, Science.

[114]  Zhuowen Tu,et al.  Parsing Images into Region and Curve Processes , 2002, ECCV.

[115]  Dale Purves,et al.  Range image statistics can explain the anomalous perception of length , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[116]  Rajesh P. N. Rao,et al.  Probabilistic Models of the Brain: Perception and Neural Function , 2002 .

[117]  T. Albright,et al.  Contextual influences on visual processing. , 2002, Annual review of neuroscience.

[118]  Michael S. Landy,et al.  Bayesian modeling of visual perception , 2002 .

[119]  Zhuowen Tu,et al.  Image Segmentation by Data-Driven Markov Chain Monte Carlo , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[120]  Paul Schrater,et al.  Shape perception reduces activity in human primary visual cortex , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[121]  S. Gepshtein,et al.  Viewing Geometry Determines How Vision and Haptics Combine in Size Perception , 2003, Current Biology.

[122]  Denis G. Pelli,et al.  The remarkable inefficiency of word recognition , 2003, Nature.

[123]  Daniel Kersten,et al.  Bootstrapped learning of novel objects. , 2003, Journal of vision.

[124]  Ione Fine,et al.  Surface segmentation based on the luminance and color statistics of natural scenes. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[125]  Tai Sing Lee,et al.  Hierarchical Bayesian inference in the visual cortex. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[126]  Alan L. Yuille,et al.  Statistical Edge Detection: Learning and Evaluating Edge Cues , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[127]  D. Knill,et al.  Bayesian and Statistical Approaches to Vision , 2003 .

[128]  D. Kersten,et al.  Three-dimensional symmetric shapes are discriminated more efficiently than asymmetric ones. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

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

[130]  Roland W Fleming,et al.  Real-world illumination and the perception of surface reflectance properties. , 2003, Journal of vision.

[131]  Alan Yuille,et al.  The KGBR viewpoint-lighting ambiguity. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[132]  Albert Yonas.  Development of space perception , 2003 .

[133]  P. Lennie.  The Cost of Cortical Computation , 2003, Current Biology.

[134]  Harriet A Allen,et al.  Visual mechanisms of motion analysis and motion perception. , 2004, Annual review of psychology.

[135]  Paul R. Schrater,et al.  How Optimal Depth Cue Integration Depends on the Task , 2000, International Journal of Computer Vision.

[136]  Eero P. Simoncelli,et al.  A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients , 2000, International Journal of Computer Vision.

[137]  D. Mumford.  On the computational architecture of the neocortex , 2004, Biological Cybernetics.

[138]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[139]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[140]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[141]  Laurence T. Maloney,et al.  Statistical Decision Theory and Biological Vision , 2005 .

[142]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.