Cubierta

Contributions to unsupervised and supervised learning with applications in digital image processing

311 p. : il.

Idioma: Spanish
Publicación: 2014
Materia:
analisis de datos
diseño de sistemas de cálculo
Acceso electrónico: http://hdl.handle.net/10810/11228
Ampliar información
id addi-10810-11228
recordtype addi
spelling addi-10810-112282021-09-29T08:35:32Zcom_10810_12140Tesis Doctoralescom_10810_91INVESTIGACIÓNcol_10810_12144TD-Ingeniería y Arquitectura Contributions to unsupervised and supervised learning with applications in digital image processing González Acuña, Ana Isabel Graña Romay, Manuel María analisis de datos diseño de sistemas de cálculo 311 p. : il. [EN]This Thesis covers a broad period of research activities with a commonthread: learning processes and its application to image processing. The twomain categories of learning algorithms, supervised and unsupervised, have beentouched across these years. The main body of initial works was devoted tounsupervised learning neural architectures, specially the Self Organizing Map.Our aim was to study its convergence properties from empirical and analyticalviewpoints.From the digital image processing point of view, we have focused on twobasic problems: Color Quantization and filter design. Both problems have beenaddressed from the context of Vector Quantization performed by CompetitiveNeural Networks. Processing of non-stationary data is an interesting paradigmthat has not been explored with Competitive Neural Networks. We have statesthe problem of Non-stationary Clustering and related Adaptive Vector Quantizationin the context of image sequence processing, where we naturally havea Frame Based Adaptive Vector Quantization. This approach deals with theproblem as a sequence of stationary almost-independent Clustering problems.We have also developed some new computational algorithms for Vector Quantizationdesign.The works on supervised learning have been sparsely distributed in time anddirection. First we worked on the use of Self Organizing Map for the independentmodeling of skin and no-skin color distributions for color based face localization. Second, we have collaborated in the realization of a supervised learning systemfor tissue segmentation in Magnetic Resonance Imaging data. Third, we haveworked on the development, implementation and experimentation with HighOrder Boltzmann Machines, which are a very different learning architecture.Finally, we have been working on the application of Sparse Bayesian Learningto a new kind of classification systems based on Dendritic Computing. This lastresearch line is an open research track at the time of writing this Thesis. 2014-04-28T19:19:21Z 2014-04-28T19:19:21Z 2012-04-17 2012-04-17 info:eu-repo/semantics/doctoralThesis 978-84-9860-697-3 DL. BI-1302-2012 http://hdl.handle.net/10810/11228 3749 3926 spa info:eu-repo/semantics/openAccess
external_data_source Addi
institution Digital
collection Addi
language Spanish
topic analisis de datos
diseño de sistemas de cálculo
spellingShingle analisis de datos
diseño de sistemas de cálculo
González Acuña, Ana Isabel
Contributions to unsupervised and supervised learning with applications in digital image processing
description 311 p. : il.
author_additional Graña Romay, Manuel María
author González Acuña, Ana Isabel
title Contributions to unsupervised and supervised learning with applications in digital image processing
title_short Contributions to unsupervised and supervised learning with applications in digital image processing
title_full Contributions to unsupervised and supervised learning with applications in digital image processing
title_fullStr Contributions to unsupervised and supervised learning with applications in digital image processing
title_full_unstemmed Contributions to unsupervised and supervised learning with applications in digital image processing
title_sort contributions to unsupervised and supervised learning with applications in digital image processing
publishDate 2014
url http://hdl.handle.net/10810/11228
_version_ 1735862633374941184

Ejemplares similares