Title:	REGULARIZED BOOTSTRAP FILTER FOR IMAGE RESTORATION
Author(s):	Bassel Marhaba and Mourad Zribi
ISBN:	978-989-8533-66-1
Editors:	Yingcai Xiao and Ajith P. Abraham
Year:	2017
Edition:	Single
Keywords:	Bootstrap Filter, Probability density function, Multivariate kernel density estimation, Particle filters, Image restoration
Type:	Full Paper
First Page:	117
Last Page:	123
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	The bootstrap filter is a method for nonlinear Bayesian filtering that uses stochastic sampling for an approximation of probability density functions. It is wide spread and perhaps the most implemented method in particle filters. It can be considered as the repetition of the sampling importance resampling over time. In this paper, we propose an image restoration method based on bootstrap filter using multivariate kernel density estimation. The multivariate Kernel density estimation of posterior density is used in the resampling step. This estimation technique makes it possible to regularize the bootstrap filter, which gives the name of the regularized bootstrap filter. Experimental results are shown to demonstrate the performance and effectiveness of our method in restoring images.
	Go Back