KERNEL METHODS FOR STATISTICAL LEARNING IN COMPUTER VISION AND PATTERN RECOGNITION APPLICATIONS

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" KERNEL METHODS FOR STATISTICAL LEARNING IN COMPUTER VISION AND PATTERN RECOGNITION APPLICATIONS "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	149945
Doc. No	:	ET21737
Main Entry	:	Refaat Mokhtar Mohamed
Title Proper	:	KERNEL METHODS FOR STATISTICAL LEARNING IN COMPUTER VISION AND PATTERN RECOGNITION APPLICATIONS
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Statistical learning-based kernel methods are rapidly replacing other empirical learning meth-ods (e.g, neural networks) as a preferred tool for machine learning due to many attractive features:a strong basis from statistical learning theory; no computational penalty in moving from linear tonon-linear models; the resulting optimization problem is convex, guaranteeing a unique global solu-tion and consequently producing systems with excellent generalization performance. This researchwork introduces statistical learning for solving different problems in computer vision and patternrecognition applications.The probability density function (pdf) estimation is a one of the major ingredients in Bayesianpattern recognition and machine learning. Many algorithms have been introduced for solving theprobability density function estimation problem either in parametric or nonparametric setup. In theparametric approach, a reasonable functional form for the probability density function is assumed,as such the problem is reduced to the parameters estimation of the functional form. For estimatinggeneral density functions, the nonpararnetric..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL44919.pdf
Title and statement of responsibility and	:	KERNEL METHODS FOR STATISTICAL LEARNING IN COMPUTER VISION AND PATTERN RECOGNITION APPLICATIONS [Thesis]