Learning to Segment Images Using Dynamic Feature Binding

Despite the fact that complex visual scenes contain multiple, overlapping objects, people perform object recognition with ease and accuracy. One operation that facilitates recognition is an early segmentation process in which features of objects are grouped and labeled according to which object they belong. Current computational systems that perform this operation are based on predefined grouping heuristics. We describe a system called MAGIC that learns how to group features based on a set of presegmented examples. In many cases, MAGIC discovers grouping heuristics similar to those previously proposed, but it also has the capability of finding nonintuitive structural regularities in images. Grouping is performed by a relaxation network that attempts to dynamically bind related features. Features transmit a complex-valued signal (amplitude and phase) to one another; binding can thus be represented by phase locking related features. MAGIC's training procedure is a generalization of recurrent backpropagation to complex-valued units.

[1]  Pierre Baldi,et al.  Computing with Arrays of Coupled Oscillators: An Application to Preattentive Texture Discrimination , 1990, Neural Computation.

[2]  Takeo Kanade,et al.  Recovery of the Three-Dimensional Shape of an Object from a Single View , 1981, Artif. Intell..

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

[4]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[5]  W. Singer,et al.  Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties , 1989, Nature.

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

[7]  Thomas O. Binford,et al.  Segmentation and aggregation: an approach to figure-ground phenomena , 1987 .

[8]  I. Rock,et al.  The legacy of Gestalt psychology. , 1990, Scientific American.

[9]  Joachim M. Buhmann,et al.  Computing with Arrays of Coupled Oscillators , 1990 .

[10]  Carsten Peterson,et al.  Rotor Neurons: Basic Formalism and Dynamics , 1992, Neural Computation.

[11]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[12]  Pineda,et al.  Generalization of back-propagation to recurrent neural networks. , 1987, Physical review letters.

[13]  A. Treisman.  Perceptual grouping and attention in visual search for features and for objects. , 1982, Journal of experimental psychology. Human perception and performance.

[14]  Bernardo A. Huberman,et al.  Binding Hierarchies: A Basis for Dynamic Perceptual Grouping , 1992, Neural Computation.

[15]  G. W. Strong,et al.  A solution to the tag-assignment problem for neural networks , 1989, Behavioral and Brain Sciences.

[16]  I. Rock,et al.  Perceptual organization and attention , 1992, Cognitive Psychology.

[17]  Edward M. Riseman,et al.  Token-based extraction of straight lines , 1989, IEEE Trans. Syst. Man Cybern..

[18]  Geoffrey E. Hinton.  A Parallel Computation that Assigns Canonical Object-Based Frames of Reference , 1981, IJCAI.

[19]  David S. Touretzky,et al.  Advances in neural information processing systems 2 , 1989 .

[20]  Reinhard Eckhorn,et al.  Feature Linking via Synchronization among Distributed Assemblies: Simulations of Results from Cat Visual Cortex , 1990, Neural Computation.

[21]  Luís B. Almeida,et al.  A learning rule for asynchronous perceptrons with feedback in a combinatorial environment , 1990 .

[22]  James L. McClelland,et al.  Computational approaches to cognition: top-down approaches , 1993, Current Opinion in Neurobiology.

[23]  Stephen Grossberg,et al.  Synchronized oscillations during cooperative feature linking in a cortical model of visual perception , 1991, Neural Networks.

[24]  J. Duncan.  Selective attention and the organization of visual information. , 1984, Journal of experimental psychology. General.

[25]  G Tononi,et al.  Modeling perceptual grouping and figure-ground segregation by means of active reentrant connections. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[26]  Allen R. Hanson,et al.  Computer Vision Systems , 1978 .

[27]  Christoph von der Malsburg,et al.  The Correlation Theory of Brain Function , 1994 .

[28]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[29]  Philip Holmes,et al.  Collective Oscillations in the Visual Cortex , 1989, NIPS.

[30]  Rakesh Mohan,et al.  Book review: PERCEPTUAL ORGANIZATION AND VISUAL RECOGNITION by David G. Lowe (Kluwer Academic Publishers) , 1987, SGAR.

[31]  David L. Waltz,et al.  Generating Semantic Descriptions From Drawings of Scenes With Shadows , 1972 .