Putting Knowledge Into a Visual Shape Representation

Abstract This paper shows how a representation for visual shape can be formulated to employ knowledge about the geometrical structures common within specific shape domains. In order to support a wide variety of later visual processing tasks, we seek representations making explicit many geometric properties and spatial relationships redundantly and at many levels of abstraction. We offer two specific computational tools: (1) By maintaining shape tokens on a Scale-Space Blackboard , information about the relative locations and sizes of shape fragments such as contours and regions can be manipulated symbolically, while the pictorial organization inherent to a shape's spatial geometry is preserved. (2) Through the device of dimensionality-reduction , configurations of shape tokens can be interpreted in terms of their membership within deformation classes ; this provides leverage in distinguishing shapes on the basis of subtle variations reflecting deformations in their forms. Using these tools, knowledge in a shape representation resides in a vocabulary of shape descriptors naming constellations of shape tokens in the Scale-Space Blackboard. The approach is illustrated through a computer implementation of a hierarchical shape vocabulary designed to offer flexibility in supporting important aspects of shape recognition and shape comparison in the two-dimensional shape domain of the dorsal fins of fishes.

[1]  Ramakant Nevatia,et al.  Description and Recognition of Curved Objects , 1977, Artif. Intell..

[2]  Eric L. Schwartz,et al.  Computational anatomy and functional architecture of striate cortex: A spatial mapping approach to perceptual coding , 1980, Vision Research.

[3]  Michael Brady,et al.  The Curvature Primal Sketch , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Alan H. Barr,et al.  Global and local deformations of solid primitives , 1984, SIGGRAPH.

[5]  James L Stansfield,et al.  Conclusions from the Commodity Expert Project , 1980 .

[6]  D. Burr.  A dynamic model for image registration , 1981 .

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

[8]  Eric Saund,et al.  Dimensionality-Reduction Using Connectionist Networks , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Michael Brady,et al.  Generating and Generalizing Models of Visual Objects , 1987, Artif. Intell..

[10]  Geoffrey E. Hinton,et al.  Symbols Among the Neurons: Details of a Connectionist Inference Architecture , 1985, IJCAI.

[11]  Eric Saund,et al.  Symbolic Construction of a 2-D Scale-Space Image , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Geoffrey E. Hinton,et al.  Learning distributed representations of concepts. , 1989 .

[13]  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.

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

[15]  Michael Leyton,et al.  A Process-Grammar for Shape , 1988, Artif. Intell..

[16]  Rodney A. Brooks,et al.  Symbolic Reasoning Among 3-D Models and 2-D Images , 1981, Artif. Intell..

[17]  Michael Leyton,et al.  Symmetry-curvature duality , 1987, Comput. Vis. Graph. Image Process..

[18]  D Marr,et al.  Early processing of visual information. , 1976, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[19]  Jonathan H Connell,et al.  Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects , 1985 .

[20]  Maureen Stone,et al.  Curve-fitting with piecewise parametric cubics , 1983, SIGGRAPH.

[21]  Dana H. Ballard,et al.  An Approach to Knowledge-Directed Image Analysis , 1977, IJCAI.

[22]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[23]  Eric Saund,et al.  Adding scale to the primal sketch , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[24]  W. A. Perkins,et al.  A Model-Based Vision System for Industrial Parts , 1978, IEEE Transactions on Computers.

[25]  S. Ullman.  Aligning pictorial descriptions: An approach to object recognition , 1989, Cognition.

[26]  M. Brady,et al.  Smoothed Local Symmetries and Their Implementation , 1984 .

[27]  Azriel Rosenfeld,et al.  ";Expert" vision systems: Some issues , 1986, Computer Vision Graphics and Image Processing.

[28]  W. Eric L. Grimson.  On the Recognition of Curved Objects , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Donald D. Hoffman,et al.  Parts of recognition , 1984, Cognition.

[30]  Eric Saund,et al.  The role of knowledge in visual shape representation , 1988 .

[31]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.