Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFusion de classifieurs pour la classification dimages sonar
249
0
0.0
(
0
)
Added by
Arnaud Martin
Publication date
2012
fields
Informatics Engineering
and research's language is
English
Authors
Arnaud Martin
Ask ChatGPT about the research
No Arabic abstract
In this paper, we present some high level information fusion approaches for numeric and symbolic data. We study the interest of such method particularly for classifier fusion. A comparative study is made in a context of sea bed characterization from sonar images. The classi- fication of kind of sediment is a difficult problem because of the data complexity. We compare high level information fusion and give the obtained performance.
rate research
Read More
The sonar images provide a rapid view of the seabed in order to characterize it. However, in such as uncertain environment, real seabed is unknown and the only information we can obtain, is the interpretation of different human experts, sometimes in conflict. In this paper, we propose to manage this conflict in order to provide a robust reality for the learning step of classification algorithms. The classification is conducted by a multilayer perceptron, taking into account the uncertainty of the reality in the learning stage. The results of this seabed characterization are presented on real sonar images.
In this chapter, we present two applications in information fusion in order to evaluate the generalized proportional conflict redistribution rule presented in the chapter cite{Martin06a}. Most of the time the combination rules are evaluated only on simple examples. We study here different combination rules and compare them in terms of decision on real data. Indeed, in real applications, we need a reliable decision and it is the final results that matter. Two applications are presented here: a fusion of human experts opinions on the kind of underwater sediments depict on sonar image and a classifier fusion for radar targets recognition.
In image classification, merging the opinion of several human experts is very important for different tasks such as the evaluation or the training. 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 image, can contain one or more kind of the considered classes given by the experts. A second problem that we have to take into account, is the amount of certainty of the expert has for each pixel of the tile. In order to solve these problems we define five models in the context of the Dempster-Shafer Theory and in the context of the Dezert-Smarandache Theory and we study the possible decisions with these models.
Many information sources are considered into data fusion in order to improve the decision in terms of uncertainty and imprecision. For each technique used for data fusion, the asumption on independance is usually made. We propose in this article an approach to take into acount an independance measure befor to make the combination of information in the context of the theory of belief functions.
This text is a study of the missing case in our article [B.91], that is to say the eigenvalue 1 case. Of course this is a more involved situation because the existence of the smooth stratum for the hypersurface {f = 0} forces to consider three strata for the nearby cycles. And we already know that the smooth stratum is always tangled if it is not alone (see [B.84b] and the introduction of [B.03]). The new phenomenon is the role played here by a new cohomology group, denote by $H^n_{ccap S}(F)_{=1}$, of the Milnors fiber of f at the origin. It has the same dimension as $H^n(F)_{=1}$ and $H^n_c(F)_{=1}$, and it leads to a non trivial factorization of the canonical map $$ can : H^n_{ccap S}(F)_{=1} to H^n_c(F)_{=1},$$ and to a monodromic isomorphism of variation $$ var :H^n_{ccap S}(F)_{=1}to H^n_c(F)_{=1}.$$ It gives a canonical hermitian form $$ mathcal{H} : H^n_{ccap S}(F)_{=1} times H^n(F )_{=1} to mathbb{C}$$ which is non degenerate. This generalizes the case of an isolated singularity for the eigenvalue 1 (see [B.90] and [B.97]). The overtangling phenomenon for strata associated to the eigenvalue 1 implies the existence of triple poles at negative integers (with big enough absolute value) for the meromorphic continuation of the distribution $int_X |f |^{2lambda}square $ for functions f having semi-simple local monodromies at each singular point of {f =0}.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
