• Corpus ID: 8881509

Learning Shape Descriptions

@inproceedings{Connell1985LearningSD,
  title={Learning Shape Descriptions},
  author={Jonathan H. Connell and Michael Brady},
  booktitle={International Joint Conference on Artificial Intelligence},
  year={1985}
}
We report on initial experiments with an implemented learning system whose inputs are images of two-dimensional shapes. The system first builds semantic network shape descriptions based on Brady's smoothed local symmetry representation. It learns shape models from them using a modified version of Winston's ANALOGY program. The learning program uses only positive examples, and is capable of learning disjunctive concepts. We discuss the lcarnability of shape descriptions. 
View Paper
ijcai.org
22 Citations
Highly Influential Citations
2
Background Citations
4
Methods Citations
2

Figures from this paper

22 Citations

Learning Graph Models of Shape

Use of Machine Learning to Generate Rules

A Similarity-Based Learning scheme is employed, that uses segmented images containing cars, to produce rules which are subsequently able to label unknown images, which are shown to be useful in developing a suitable Knowledge Representation for this vision problem.

Steps toward making robots see

This paper reports on recent progress in Computer Vision by the Oxford Robotics Research Group. We discuss in particular: edge and corner finding; shape from contour; parallel algorithms for…

Model learning and recognition of nonrigid objects

  • J. Segen
  • Computer Science
    Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 1989
A method of learning structural models of 2D shape from real data using a fast graph-matching heuristic which seeks a simplest representation of a graph, which makes it possible to apply the system to any set of shape data without adjustments.

Learning Visual Models from Shape Contours Using Multiscale Convex/Concave Structure Matching

A novel approach is proposed for learning a visual model from real shape samples of the same class by generalizing the multiscale convex/concave structure of a class of shapes based on the concept that shape generalization is shape simplification wherein perceptually relevant features are retained.

Inference of Stochastic Graph Models for 2-D and 3-D Shapes

The use of a stochastic graph as a model for a class of 2-D or 3-D shapes is described, and learning methods that infer stoChastic graph models and their symbolic primitives from examples are presented.

FORMS: A flexible object recognition and modelling system

A model for generating the shapes of animate objects which gives a formalism for solving the inverse problem of object recognition and how such a representation scheme can be automatically learnt from examples is described.

The Curvature Primal Sketch

  • H. AsadaM. Brady
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1986
An implemented algorithm is described that computes the Curvature Primal Sketch by matching the multiscale convolutions of a shape, and its performance on a set of tool shapes is illustrated.

Representing Space for Practical Reasoning

Graph Clustering and Model Learning by Data Compression

References

SHOWING 1-10 OF 31 REFERENCES

Representation and recognition of the spatial organization of three-dimensional shapes

  • D. MarrH. Nishihara
  • Computer Science
    Proceedings of the Royal Society of London. Series B. Biological Sciences
  • 1978
The human visual process can be studied by examining the computational problems associated with deriving useful information from retinal images. In this paper, we apply this approach to the problem…

Symbolic Reasoning Among 3-D Models and 2-D Images

Criteria for Representations of Shape

Representing Smooth Plane Curves for Recognition: Implications for Figure-Ground Reversal

Psychophysical observations regarding the perception of figureground reversals arc are presented to suggest that a similar representation of smooth plane curves for recognition could be used by the human visual system.

Learning Physical Descriptions From Functional Definitions, Examples, and Precedents

The theory is a synthesis of two sets of ideas: ideas about learning from precedents and exercises developed at MIT and ideas about physical description developed at Stanford, and is illustrated by way of representative experiments.

Description and Recognition of Curved Objects

A Model-Based Vision System for Industrial Parts

A vision system has been developed which can determine the position and orientation of complex curved objects in gray-level noisy scenes. The system organizes and reduces the image data from a…

Smoothed Local Symmetries and Their Implementation

The main features of the SLS repre sentation are developed and an implemented algorithm that com putes it is described and illustrated for a set of tools.

Understanding Image Intensities

On Overview of KRL, a Knowledge Representation Language

KRL is an attempt to integrate procedural knowledge with a broad base of declarative forms to give flexibility in associating procedures with specific pieces of knowledge, and to control the relative accessibility of different facts and descriptions.