國立虎尾科技大學 |

Visual Texture Analysis for Material Understanding.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Visual Texture Analysis for Material Understanding./
作者:	Nguyen, Dzung.
面頁冊數:	1 online resource (62 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
Contained By:	Dissertation Abstracts International79-08B(E).
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9780355824520

Visual Texture Analysis for Material Understanding.
Nguyen, Dzung.

Visual Texture Analysis for Material Understanding. - 1 online resource (62 pages)

Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.

Thesis (Ph.D.)--Northwestern University, 2018.

Includes bibliographical references

Texture is an important visual attribute for both human perception and image analysis. It provides useful information for object and scene understanding. However, unlike other computer vision techniques that focus on object shape, texture analysis provides important clues for material understanding. The focus of this thesis is on material identification from texture images. This is a challenging problem that has not received adequate attention. It is important for a variety of applications including surveillance and security, environmental monitoring, agriculture and forestry, health, product design, and sense substitution.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355824520Subjects--Topical Terms:

596380
Electrical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Visual Texture Analysis for Material Understanding.
LDR:03477ntm a2200373Ki 4500 001 918346
005 20181114145235.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780355824520
035 $a (MiAaPQ)AAI10688986
035 $a (MiAaPQ)northwestern:14016
035 $a AAI10688986
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Nguyen, Dzung. $3 1192646
245 1 0 $a Visual Texture Analysis for Material Understanding.
264 0 $c 2018
300 $a 1 online resource (62 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
500 $a Adviser: Thrasyvoulos N. Pappas.
502 $a Thesis (Ph.D.)--Northwestern University, 2018.
504 $a Includes bibliographical references
520 $a Texture is an important visual attribute for both human perception and image analysis. It provides useful information for object and scene understanding. However, unlike other computer vision techniques that focus on object shape, texture analysis provides important clues for material understanding. The focus of this thesis is on material identification from texture images. This is a challenging problem that has not received adequate attention. It is important for a variety of applications including surveillance and security, environmental monitoring, agriculture and forestry, health, product design, and sense substitution.
520 $a The proposed techniques account for dramatic changes in texture appearance due to variations in illumination and viewing conditions. The key elements of the proposed approach are (1) an adaptation of the Visual Similarity by Progressive Grouping (ViSiProG) procedure for identifying clusters of visually similar textures (2) the characterization of each material with a small set of exemplars; (3) the use of machine learning techniques for training of Structural Texture Similarity Metrics (STSIMs) to agree with human perception based on clusters from ViSiProG, and as a result, to be able to separate the textures according to the material they correspond to.
520 $a Human perception has long been considered as a benchmark for computer vision and image analysis applications. However, current human-based annotation methods mostly deal with application outputs. Instead, we explore the possibilities of capturing human perception at a lower level (visual similarity of images), and utilize a learning framework for metric adaptation.
520 $a We demonstrate the effectiveness of the proposed techniques using "CUReT," a fully labeled database of real-world surfaces, viewed under different illuminations and viewing angles at a fixed distance. However, the proposed approaches can be applied to different domains, especially when semantic labeling is not available, for example in an unlabeled database of satellite images, which offers a much wider range of materials, illuminations, and viewing angles, and an unlabeled database of building fronts obtained from "Google Earth Street View."
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Northwestern University. $b Electrical and Computer Engineering. $3 1186892
773 0 $t Dissertation Abstracts International $g 79-08B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10688986 $z click for full text (PQDT)