Human expert fusion for image classification

@article{Martin2008HumanEF,
  title={Human expert fusion for image classification},
  author={Arnaud Martin and Christophe Osswald},
  journal={ArXiv},
  year={2008},
  volume={abs/0806.1798}
}
In image classification, merging the opinion of several huma n experts is very important for different tasks such as the evaluation or the t raining. Indeed, the ground truth is rarely known before the scene imaging. We propose here different models in order to fuse the informations given by two or more experts. The considered unit for the classification, a small tile of the im age, can contain one or more kind of the considered classes given by the experts. A second problem that we have to… Expand
Fusion of heterogeneous remote sensing images by credibilist methods. (Fusion d'images de télédétection hétérogènes par méthodes crédibilistes)
TLDR
This thesis focuses on the development of a new approach for the belief functions estimation based on Kohonen's map in order to simplify the masses assignment operation of the large volumes of data occupied by these images, and proposes an original fusion technique that will solve problems due to the wide variety of knowledge provided by these heterogeneous sensors. Expand
Fusion d'images par la théorie de Dezert-Smarandache (DSmT) en vue d'applications en télédétection
The main objective of this thesis is to provide automatic remote sensing tools of classi cation and of change detection of land cover for many purposes, in this context, we have developed two generalExpand
Generalized proportional conflict redistribution rule applied to Sonar imagery and Radar targets classification
TLDR
This chapter presents the advantages of the DSmT for the modelization of real applications and also for the combination step, and presents the formalization of the belief functionmodels, different rules of combination and decision. Expand
Understanding the large family of Dempster-Shafer theory's fusion operators - a decision-based measure
TLDR
All the fusion operators tested with random belief functions are validated on the fusion of radar data classifiers, and show the interest of some new PCR methods. Expand
Toward Efficient Computation of the
Dempster-Shafer (DS) belief theory provides a con- venient framework for the development of powerful data fusion engines by allowing for a convenient representation of a wide variety of dataExpand
Evidence combination for a large number of sources
TLDR
A combination rule for a large number of sources, named LNS (stands for Large Number of Sources), is proposed on the basis of a simple idea: the more common ideas one source shares with others, the more reliable the source is. Expand
Conflict management in information fusion with belief functions
  • Arnaud Martin
  • Computer Science
  • Information Quality in Information Fusion and Decision Making
  • 2019
TLDR
This chapter proposes a discussion to consider the conflict in information fusion with the theory of belief functions and some approaches have been proposed in order to manage this conflict or to decide with conflicting mass functions. Expand
Belief Detection and Temporal Analysis of Experts in Question Answering Communities: case study Stack Overflow. (Détection et Analyse Temporelle des Experts dans les Réseaux Communautaires de Questions Réponses : étude de cas Stack Overflow)
TLDR
A general measure of expertise based on the theory of belief functions is proposed, which will allow us to classify users and detect the most knowledgeable persons, and how do users evolve during their time spent within the platform is described. Expand
Influencers characterization in a social network for viral marketing perspectives. (Caractérisation des influenceurs dans un réseau social pour des perspectives de Marketing viral)
TLDR
This thesis proposes two evidential influence maximization models for social networks that uses the theory of belief functions to estimate users influence and introduces an influence measure that fuses many influence aspects, like the importance of the user in the network and the popularity of his messages. Expand

References

SHOWING 1-10 OF 30 REFERENCES
Comparative study of information fusion methods for sonar images classification
  • A. Martin
  • Computer Science
  • 2005 7th International Conference on Information Fusion
  • 2005
TLDR
A comparative study of information fusion methods for sonar images classification using the weighted vote approach, or coming from the possibility theory and evidence theory, have been employed. Expand
Methods of combining multiple classifiers and their applications to handwriting recognition
TLDR
On applying these methods to combine several classifiers for recognizing totally unconstrained handwritten numerals, the experimental results show that the performance of individual classifiers can be improved significantly. Expand
Application of majority voting to pattern recognition: an analysis of its behavior and performance
  • L. Lam, C. Suen
  • Computer Science
  • IEEE Trans. Syst. Man Cybern. Part A
  • 1997
TLDR
This paper examines the mode of operation of the majority vote method in order to gain a deeper understanding of how and why it works, so that a more solid basis can be provided for its future applications to different data and/or domains. Expand
Representation and combination of uncertainty with belief functions and possibility measures
TLDR
The framework of belief functions in terms of expressive power for knowledge representation is examined and it is indicated that combination rules issued from fuzzy set and possibility theory look more flexible than Dempster rule because many variants exist, and their numerical stability seems to be better. Expand
Information fusion based on new proportional conflict redistribution rules
TLDR
This paper proposes anew family of fusion rules for the combination of uncertainty and conflicting information, based on new Proportional Conflict Redistributions (PCR) allowing us to deal with highly conflicting sources for static and dynamic fusion applications. Expand
Upper and Lower Probabilities Induced by a Multivalued Mapping
  • A. Dempster
  • Mathematics, Computer Science
  • Classic Works of the Dempster-Shafer Theory of Belief Functions
  • 2008
TLDR
A distinctive feature of the present approach is a rule for conditioning, or more generally, arule for combining sources of information, as discussed in Sects. Expand
On the dempster-shafer framework and new combination rules
  • R. Yager
  • Mathematics, Computer Science
  • Inf. Sci.
  • 1987
TLDR
The basic concepts of the Dempster-Shafer approach, basic probability assignments, belief functions, and probability functions are discussed, and how to represent various types of knowledge in this framework is discussed. Expand
Belief functions: The disjunctive rule of combination and the generalized Bayesian theorem
  • P. Smets
  • Mathematics, Computer Science
  • Int. J. Approx. Reason.
  • 1993
TLDR
The Bayes’ theorem is generalized within the transferable belief model framework and the DRC and GBT and their uses for belief propagation in directed belief networks are analysed. Expand
Belief Functions: The Disjunctive Rule of Combination and the Generalized Bayesian Theorem
  • P. Smets
  • Mathematics, Computer Science
  • Classic Works of the Dempster-Shafer Theory of Belief Functions
  • 2008
TLDR
The Bayes’ theorem is generalized within the transferable belief model framework and the properties of the DRC and GBT and their uses for belief propagation in directed belief networks are analysed. Expand
Fuzzy sets as a basis for a theory of possibility
The theory of possibility described in this paper is related to the theory of fuzzy sets by defining the concept of a possibility distribution as a fuzzy restriction which acts as an elasticExpand
...
1
2
3
...