Authors:
Sio-Song Ieng
1
;
Jean-Philippe Tarel
2
and
Pierre Charbonnier
3
Affiliations:
1
ERA 17 LCPC, Laboratoire des Ponts et Chaussées, France
;
2
ESE, Laboratoire Central des Ponts et Chaussées, France
;
3
ERA 27 LCPC, Laboratoire des Ponts et Chaussées, France
Keyword(s):
Image Analysis, Statistical Approach, Noise Modeling, Robust Fitting, Image Grouping and Segmentation, Image Enhancement.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Enhancement and Restoration
;
Image and Video Analysis
;
Image Formation and Preprocessing
;
Statistical Approach
Abstract:
Accurate noise models are important to perform reliable robust image analysis. Indeed, many vision problems can be seen as parameter estimation problems. In this paper, two noise models are presented and we show that these models are convenient to approximate observation noise in different contexts related to image analysis. In spite of the numerous results on M-estimators, their robustness is not always clearly addressed in the image analysis field. Based on Mizera and Mu¨ ller’s recent fundamental work, we study the robustness of M-estimators for the two presented noise models, in the fixed design setting. To illustrate the interest of these noise models, we present two image vision applications that can be solved within this framework: curves fitting and edge-preserving image smoothing.