Scene analysis using region-based constraint filtering

Abstract A general-purpose scene-analysis system is described which uses constraint-filtering techniques to apply domain knowledge in the interpretation of the regions extracted from a segmented image. An example is given of the configuration of the system for a particular domain, FLIR (Forward Looking InfraRed) images, as well as results of the system's performance on some typical images from this domain. A number of improvements to these techniques are proposed.

[1]  Leslie J. Kitchen,et al.  Fast, parallel, relaxation screening for chemical patent data-base search , 1982, J. Chem. Inf. Comput. Sci..

[2]  Olivier D. Faugeras,et al.  Improving Consistency and Reducing Ambiguity in Stochastic Labeling: An Optimization Approach , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  L. Kitchen.  Discrete Relaxation for Matching Relational Structures , 1978 .

[4]  Harry G. Barrow,et al.  Representation and use of knowledge in vision , 1975, SGAR.

[5]  L. S. Davis,et al.  A Logic Model for Constraint Propagation , 1980 .

[6]  Robert M. Haralick,et al.  Increasing Tree Search Efficiency for Constraint Satisfaction Problems , 1979, Artif. Intell..

[7]  Alan K. Mackworth.  Consistency in Networks of Relations , 1977, Artif. Intell..

[8]  John Gaschnig,et al.  A General Backtrack Algorithm That Eliminates Most Redundant Tests , 1977, IJCAI.

[9]  Robert M. Haralick,et al.  Arrangements, Homomorphisms, and Discrete Relaxation , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[10]  R. Kirby.  A product rule relaxation method , 1980 .

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

[12]  R M Haralick,et al.  The consistent labeling problem: part I. , 1979, IEEE transactions on pattern analysis and machine intelligence.

[13]  J. J. McGregor.  Relational consistency algorithms and their application in finding subgraph and graph isomorphisms , 1979, Inf. Sci..

[14]  Jan-Olof Eklundh,et al.  Some properties of stochastic labeling procedures , 1982, Comput. Graph. Image Process..

[15]  J M Tenenbaum,et al.  MSYS: A System for Reasoning About Scenes. , 1975 .

[16]  Julian R. Ullmann,et al.  An Algorithm for Subgraph Isomorphism , 1976, J. ACM.

[17]  David L. Waltz,et al.  Understanding Line drawings of Scenes with Shadows , 1975 .

[18]  Azriel Rosenfeld,et al.  Scene Labeling by Relaxation Operations , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[19]  Larry S. Davis,et al.  Hierarchical Constraint Processes for Shape Analysis , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Patrick Henry Winston,et al.  Learning structural descriptions from examples , 1970 .

[21]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Olivier D. Faugeras,et al.  Semantic Description of Aerial Images Using Stochastic Labeling , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Shmuel Peleg,et al.  A New Probabilistic Relaxation Scheme , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Jerome A. Feldman,et al.  Decision Theory and Artificial Intelligence: I. A Semantics-Based Region Analyzer , 1974, Artif. Intell..

[25]  Les Kitchen,et al.  Relaxation Applied to Matching Quantitative Relational Structures , 1978 .

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

[27]  Harry G. Barrow,et al.  Experiments in Interpretation-Guided Segmentation , 1977, Artificial Intelligence.