Improving Consistency and Reducing Ambiguity in Stochastic Labeling: An Optimization Approach
- 1 July 1981
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. PAMI-3 (4) , 412-424
- https://doi.org/10.1109/tpami.1981.4767127
Abstract
We approach the problem of labeling a set of objects from a quantitative standpoint. We define a world model in terms of transition probabilities and propose a definition of a class of global criteria that combine both ambiguity and consistency. A projected gradient algorithm is developed to minimize the criterion. We show that the minimization procedure can be implemented in a highly parallel manner. Results are shown on several examples and comparisons are made with relaxation labeling techniques.Keywords
This publication has 9 references indexed in Scilit:
- A New Probabilistic Relaxation SchemePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1980
- Decorrelation Methods of Texture Feature ExtractionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1980
- Scene labeling: an optimization approachPattern Recognition, 1980
- Relaxation and constrained optimization by local processesComputer Graphics and Image Processing, 1979
- Relaxation Processes for Scene Labeling: Convergence, Speed, and StabilityIEEE Transactions on Systems, Man, and Cybernetics, 1978
- An Application of Relaxation Labeling to Line and Curve EnhancementIEEE Transactions on Computers, 1977
- Structural Pattern RecognitionPublished by Springer Nature ,1977
- Scene Labeling by Relaxation OperationsIEEE Transactions on Systems, Man, and Cybernetics, 1976
- The Gradient Projection Method for Nonlinear Programming. Part I. Linear ConstraintsJournal of the Society for Industrial and Applied Mathematics, 1960