東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Graph-Based Models and Transforms fo...

Egilmez, Hilmi Enes.

Linked to FindBook

Google Book

Amazon

博客來

Graph-Based Models and Transforms for Signal/data Processing With Applications to Video Coding.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Graph-Based Models and Transforms for Signal/data Processing With Applications to Video Coding./
Author:	Egilmez, Hilmi Enes.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
Description:	135 p.
Notes:	Source: Dissertation Abstracts International, Volume: 79-06(E), Section: B.
Contained By:	Dissertation Abstracts International79-06B(E).
Subject:	Electrical engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10820433

Graph-Based Models and Transforms for Signal/data Processing With Applications to Video Coding.
Egilmez, Hilmi Enes.

Graph-Based Models and Transforms for Signal/data Processing With Applications to Video Coding. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 135 p.

Source: Dissertation Abstracts International, Volume: 79-06(E), Section: B.

Thesis (Ph.D.)--University of Southern California, 2017.

Graphs are fundamental mathematical structures used in various fields to represent data, signals and processes. Particularly in signal processing, machine learning and statistics, structured modeling of signals and data by means of graphs is essential for a broad number of applications. In this thesis, we develop novel techniques to build graph-based models and transforms for signal/data processing, where the models and transforms of interest are defined based on graph Laplacian matrices. For graph-based modeling, various graph Laplacian estimation problems are studied. Firstly, we consider estimation of three types of graph Laplacian matrices from data and develop efficient algorithms by incorporating associated Laplacian and structural constraints. Then, we propose a graph signal processing framework to learn graph-based models from classes of filtered signals, defined based on functions of graph Laplacians. The proposed approach can also be applied to learn diffusion (heat) kernels, which are popular in various fields for modeling diffusion processes. Additionally, we study the problem of multigraph combining, which is estimating a single optimized graph from multiple graphs, and develop an algorithm. Finally, we propose graph-based transforms for video coding and develop two different techniques, based on graph learning and image edge adaptation, to design orthogonal transforms capturing the statistical characteristics of video signals. Theoretical justifications and comprehensive experimental results for the proposed methods are presented.Subjects--Topical Terms:

649834
Electrical engineering.

Graph-Based Models and Transforms for Signal/data Processing With Applications to Video Coding.
LDR:02498nmm a2200277 4500 001 2165147
005 20181129115240.5
008 190424s2017 ||||||||||||||||| ||eng d
035 $a (MiAaPQ)AAI10820433
035 $a (MiAaPQ)US_Calif_427945
035 $a AAI10820433
040 $a MiAaPQ $c MiAaPQ
100 1 $a Egilmez, Hilmi Enes. $3 3353212
245 1 0 $a Graph-Based Models and Transforms for Signal/data Processing With Applications to Video Coding.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 135 p.
500 $a Source: Dissertation Abstracts International, Volume: 79-06(E), Section: B.
500 $a Adviser: Antonio Ortega.
502 $a Thesis (Ph.D.)--University of Southern California, 2017.
520 $a Graphs are fundamental mathematical structures used in various fields to represent data, signals and processes. Particularly in signal processing, machine learning and statistics, structured modeling of signals and data by means of graphs is essential for a broad number of applications. In this thesis, we develop novel techniques to build graph-based models and transforms for signal/data processing, where the models and transforms of interest are defined based on graph Laplacian matrices. For graph-based modeling, various graph Laplacian estimation problems are studied. Firstly, we consider estimation of three types of graph Laplacian matrices from data and develop efficient algorithms by incorporating associated Laplacian and structural constraints. Then, we propose a graph signal processing framework to learn graph-based models from classes of filtered signals, defined based on functions of graph Laplacians. The proposed approach can also be applied to learn diffusion (heat) kernels, which are popular in various fields for modeling diffusion processes. Additionally, we study the problem of multigraph combining, which is estimating a single optimized graph from multiple graphs, and develop an algorithm. Finally, we propose graph-based transforms for video coding and develop two different techniques, based on graph learning and image edge adaptation, to design orthogonal transforms capturing the statistical characteristics of video signals. Theoretical justifications and comprehensive experimental results for the proposed methods are presented.
590 $a School code: 0208.
650 4 $a Electrical engineering. $3 649834
690 $a 0544
710 2 $a University of Southern California. $3 700129
773 0 $t Dissertation Abstracts International $g 79-06B(E).
790 $a 0208
791 $a Ph.D.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10820433