Abstract
This chapter formulates a framework for a maximum likelihood approach in computer vision applications. It begins by introducing basic concepts from robust statistics including the outliers generation mechanisms. Further, we present the classical robust estimation procedure with an emphasis on Hampel’s approach [Hampel et al., 1986] based on influence functions. The maximum likelihood relation with other approaches is also investigated. We draw on the ideas of robust estimation and influence functions in formulating problems in which similarity is provided by a ground truth. Our goal is to find the probability density function which maximizes the similarity probability. Furthermore, we illustrate our approach based on maximum likelihood which consists of finding the best metric to be used in an application when the ground truth is provided.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Sebe, N., Lew, M.S. (2003). Maximum Likelihood Framework. In: Robust Computer Vision. Computational Imaging and Vision, vol 26. Springer, Dordrecht. https://doi.org/10.1007/978-94-017-0295-9_2
Download citation
DOI: https://doi.org/10.1007/978-94-017-0295-9_2
Publisher Name: Springer, Dordrecht
Print ISBN: 978-90-481-6290-1
Online ISBN: 978-94-017-0295-9
eBook Packages: Springer Book Archive