大葉大學圖書館 |

Computational texture and patterns :from textons to deep learning /

紀錄類型:	書目-電子資源 : Monograph/item
杜威分類號:	006.4
書名/作者:	Computational texture and patterns : : from textons to deep learning // Kristin J. Dana.
作者:	Dana, Kristin J.,
面頁冊數:	1 PDF (xiii, 99 pages) : : illustrations.
附註:	Part of: Synthesis digital library of engineering and computer science.
標題:	Pattern recognition systems.
標題:	Texture mapping.
ISBN:	9781681730127
書目註:	Includes bibliographical references (pages 77-98).
內容註:	1. Visual patterns and texture -- 1.1 Patterns in nature -- 1.2 Big data patterns -- 1.3 Temporal patterns -- 1.4 Organization --
摘要、提要註:	Visual pattern analysis is a fundamental tool in mining data for knowledge. Computational representations for patterns and texture allow us to summarize, store, compare, and label in order to learn about the physical world. Our ability to capture visual imagery with cameras and sensors has resulted in vast amounts of raw data, but using this information effectively in a task-specific manner requires sophisticated computational representations. We enumerate specific desirable traits for these representations: (1) intraclass invariance--to support recognition; (2) illumination and geometric invariance for robustness to imaging conditions; (3) support for prediction and synthesis to use the model to infer continuation of the pattern; (4) support for change detection to detect anomalies and perturbations; and (5) support for physics-based interpretation to infer system properties from appearance. In recent years, computer vision has undergone a metamorphosis with classic algorithms adapting to new trends in deep learning. This text provides a tour of algorithm evolution including pattern recognition, segmentation and synthesis. We consider the general relevance and prominence of visual pattern analysis and applications that rely on computational models.
電子資源:	https://ieeexplore.ieee.org/servlet/opac?bknumber=8467550

Computational texture and patterns :from textons to deep learning /
Dana, Kristin J.,1968-

Computational texture and patterns :from textons to deep learning /Kristin J. Dana. - 1 PDF (xiii, 99 pages) :illustrations. - Synthesis lectures on computer vision,# 142153-1064 ;. - Synthesis digital library of engineering and computer science..

Part of: Synthesis digital library of engineering and computer science.

Includes bibliographical references (pages 77-98).

1. Visual patterns and texture -- 1.1 Patterns in nature -- 1.2 Big data patterns -- 1.3 Temporal patterns -- 1.4 Organization --

Abstract freely available; full-text restricted to subscribers or individual document purchasers.

Compendex

Visual pattern analysis is a fundamental tool in mining data for knowledge. Computational representations for patterns and texture allow us to summarize, store, compare, and label in order to learn about the physical world. Our ability to capture visual imagery with cameras and sensors has resulted in vast amounts of raw data, but using this information effectively in a task-specific manner requires sophisticated computational representations. We enumerate specific desirable traits for these representations: (1) intraclass invariance--to support recognition; (2) illumination and geometric invariance for robustness to imaging conditions; (3) support for prediction and synthesis to use the model to infer continuation of the pattern; (4) support for change detection to detect anomalies and perturbations; and (5) support for physics-based interpretation to infer system properties from appearance. In recent years, computer vision has undergone a metamorphosis with classic algorithms adapting to new trends in deep learning. This text provides a tour of algorithm evolution including pattern recognition, segmentation and synthesis. We consider the general relevance and prominence of visual pattern analysis and applications that rely on computational models.

Mode of access: World Wide Web.

ISBN: 9781681730127

Standard No.: 10.2200/S00819ED1V01Y201712COV014doiSubjects--Topical Terms:

189561
Pattern recognition systems.
Subjects--Index Terms:

texture

LC Class. No.: TK7882.P3 / D253 2018

Dewey Class. No.: 006.4

Computational texture and patterns :from textons to deep learning /
LDR:05225nmm 2200709 i 4500 001 509144
003 IEEE
005 20180926145955.0
006 m eo d
007 cr cn |||m|||a
008 210514s2018 caua foab 000 0 eng d
020 $a 9781681730127 $q ebook
020 $z 9781681732695 $q hardcover
020 $z 9781681730110 $q paperback
024 7 $a 10.2200/S00819ED1V01Y201712COV014 $2 doi
035 $a (CaBNVSL)swl000408686
035 $a (OCoLC)1054358004
035 $a 8467550
040 $a CaBNVSL $b eng $e rda $c CaBNVSL $d CaBNVSL
050 4 $a TK7882.P3 $b D253 2018
082 0 4 $a 006.4 $2 23
100 1 $a Dana, Kristin J., $d 1968- $e author. $3 728995
245 1 0 $a Computational texture and patterns : $b from textons to deep learning / $c Kristin J. Dana.
264 1 $a [San Rafael, California] : $b Morgan & Claypool, $c 2018.
300 $a 1 PDF (xiii, 99 pages) : $b illustrations.
336 $a text $2 rdacontent
337 $a electronic $2 isbdmedia
338 $a online resource $2 rdacarrier
490 1 $a Synthesis lectures on computer vision, $x 2153-1064 ; $v # 14
500 $a Part of: Synthesis digital library of engineering and computer science.
504 $a Includes bibliographical references (pages 77-98).
505 0 $a 1. Visual patterns and texture -- 1.1 Patterns in nature -- 1.2 Big data patterns -- 1.3 Temporal patterns -- 1.4 Organization --
505 8 $a 2. Textons in human and computer vision -- 2.1 Pre-attentive vision -- 2.2 Texton: the early definition -- 2.3 What are textons? Then and now --
505 8 $a 3. Texture recognition -- 3.1 Traditional methods of texture recognition -- 3.2 From textons to deep learning for recognition -- 3.3 Texture recognition with deep learning -- 3.4 Material recognition vs. texture recognition --
505 8 $a 4. Texture segmentation -- 4.1 Traditional methods of texture segmentation -- 4.1.1 Graph-based methods -- 4.1.2 Mean shift methods -- 4.1.3 Markov random fields -- 4.2 Segmentation with deep learning --
505 8 $a 5. Texture synthesis -- 5.1 Traditional methods for texture synthesis -- 5.2 Texture synthesis with deep learning --
505 8 $a 6. Texture style transfer -- 6.1 Traditional methods of style transfer -- 6.2 Texture style transfer with deep learning -- 6.3 Face style transfer --
505 8 $a 7. Return of the pyramids -- 7.1 Advantages of pyramid methods --
505 8 $a 8. Open issues in understanding visual patterns -- 8.1 Discovering unknown patterns -- 8.2 Detecting subtle change -- 8.3 Perceptual metrics --
505 8 $a 9. Applications for texture and patterns -- 9.1 Medical imaging and quantitative dermatology -- 9.2 Texture matching in industry -- 9.3 E-commerce -- 9.4 Textured solar panels -- 9.5 Road analysis for automated driving --
505 8 $a 10. Tools for mining patterns: cloud services and software libraries -- 10.1 Software libraries -- 10.2 Cloud services --
505 8 $a A. A concise description of deep learning -- A.1 Multilayer perceptron -- A.2 Convolutional neural networks -- A.3 Alexnet, Dense-Net, Res-Nets, and all that --
505 8 $a Bibliography -- Author's biography.
506 $a Abstract freely available; full-text restricted to subscribers or individual document purchasers.
510 0 $a Compendex
510 0 $a INSPEC
510 0 $a Google scholar
510 0 $a Google book search
520 3 $a Visual pattern analysis is a fundamental tool in mining data for knowledge. Computational representations for patterns and texture allow us to summarize, store, compare, and label in order to learn about the physical world. Our ability to capture visual imagery with cameras and sensors has resulted in vast amounts of raw data, but using this information effectively in a task-specific manner requires sophisticated computational representations. We enumerate specific desirable traits for these representations: (1) intraclass invariance--to support recognition; (2) illumination and geometric invariance for robustness to imaging conditions; (3) support for prediction and synthesis to use the model to infer continuation of the pattern; (4) support for change detection to detect anomalies and perturbations; and (5) support for physics-based interpretation to infer system properties from appearance. In recent years, computer vision has undergone a metamorphosis with classic algorithms adapting to new trends in deep learning. This text provides a tour of algorithm evolution including pattern recognition, segmentation and synthesis. We consider the general relevance and prominence of visual pattern analysis and applications that rely on computational models.
530 $a Also available in print.
538 $a Mode of access: World Wide Web.
538 $a System requirements: Adobe Acrobat Reader.
588 $a Title from PDF title page (viewed on September 26, 2018).
650 0 $a Pattern recognition systems. $3 189561
650 0 $a Texture mapping. $3 728996
653 $a texture
653 $a patterns
653 $a deep learning
653 $a machine learning
653 $a segmentation
653 $a synthesis
653 $a recognition
653 $a textons
653 $a style transfer
776 0 8 $i Print version: $z 9781681730110 $z 9781681732695
830 0 $a Synthesis digital library of engineering and computer science. $3 461208
830 0 $a Synthesis lectures on computer vision ; $v #9. $x 2153-1056 $3 713984
856 4 2 $3 Abstract with links to resource $u https://ieeexplore.ieee.org/servlet/opac?bknumber=8467550