南開科技大學圖書館 |

言語: 日文

ヘルプ

南開科技大學

圖書館首頁

編目中圖書申請

ログイン

ホームページ

スイッチ: ラベル | MARC形式 | 国際標準書誌記述(ISBD)

Tensor VotingA Perceptual Organizati...

Medioni, Gérard.

Tensor VotingA Perceptual Organization Approach to Computer Vision and Machine Learning /

レコード種別:	コンピュータ・メディア : 単行資料
タイトル / 著者:	Tensor Voting/ by Philippos Mordohai, Gérard Medioni.
その他のタイトル:	A Perceptual Organization Approach to Computer Vision and Machine Learning /
著者:	Mordohai, Philippos.
その他の著者:	Medioni, Gérard.
記述:	IX, 126 p.online resource.
含まれています:	Springer Nature eBook
主題:	Engineering. -
電子資源:	Fulltext (查閱電子書全文)
国際標準図書番号 (ISBN):	9783031022425

Tensor VotingA Perceptual Organization Approach to Computer Vision and Machine Learning /
Mordohai, Philippos.

Tensor VotingA Perceptual Organization Approach to Computer Vision and Machine Learning /[electronic resource] :by Philippos Mordohai, Gérard Medioni. - 1st ed. 2006. - IX, 126 p.online resource. - Synthesis Lectures on Image, Video, and Multimedia Processing,1559-8144. - Synthesis Lectures on Image, Video, and Multimedia Processing,.

Introduction -- Tensor Voting -- Stereo Vision from a Perceptual Organization Perspective -- Tensor Voting in ND -- Dimensionality Estimation, Manifold Learning and Function Approximation -- Boundary Inference -- Figure Completion -- Conclusions.

This lecture presents research on a general framework for perceptual organization that was conducted mainly at the Institute for Robotics and Intelligent Systems of the University of Southern California. It is not written as a historical recount of the work, since the sequence of the presentation is not in chronological order. It aims at presenting an approach to a wide range of problems in computer vision and machine learning that is data-driven, local and requires a minimal number of assumptions. The tensor voting framework combines these properties and provides a unified perceptual organization methodology applicable in situations that may seem heterogeneous initially. We show how several problems can be posed as the organization of the inputs into salient perceptual structures, which are inferred via tensor voting. The work presented here extends the original tensor voting framework with the addition of boundary inference capabilities; a novel re-formulation of the framework applicable to high-dimensional spaces and the development of algorithms for computer vision and machine learning problems. We show complete analysis for some problems, while we briefly outline our approach for other applications and provide pointers to relevant sources.

ISBN: 9783031022425

Standard No.: 10.1007/978-3-031-02242-5doiSubjects--Topical Terms:

162510
Engineering.

LC Class. No.: T1-995

Dewey Class. No.: 620

Tensor VotingA Perceptual Organization Approach to Computer Vision and Machine Learning /
LDR:02885nmm a22003735i 4500 001 1000127465
003 DE-He213
005 20220601133547.0
007 cr nn 008mamaa
008 220601s2006 sz | s |||| 0|eng d
020 $a 9783031022425 $9 978-3-031-02242-5
024 7 $a 10.1007/978-3-031-02242-5 $2 doi
035 $a 978-3-031-02242-5
050 4 $a T1-995
072 7 $a TBC $2 bicssc
072 7 $a TEC000000 $2 bisacsh
072 7 $a TBC $2 thema
082 0 4 $a 620 $2 23
100 1 $a Mordohai, Philippos. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1000149569
245 1 0 $a Tensor Voting $h [electronic resource] : $b A Perceptual Organization Approach to Computer Vision and Machine Learning / $c by Philippos Mordohai, Gérard Medioni.
250 $a 1st ed. 2006.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2006.
300 $a IX, 126 p. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a Synthesis Lectures on Image, Video, and Multimedia Processing, $x 1559-8144
505 0 $a Introduction -- Tensor Voting -- Stereo Vision from a Perceptual Organization Perspective -- Tensor Voting in ND -- Dimensionality Estimation, Manifold Learning and Function Approximation -- Boundary Inference -- Figure Completion -- Conclusions.
520 $a This lecture presents research on a general framework for perceptual organization that was conducted mainly at the Institute for Robotics and Intelligent Systems of the University of Southern California. It is not written as a historical recount of the work, since the sequence of the presentation is not in chronological order. It aims at presenting an approach to a wide range of problems in computer vision and machine learning that is data-driven, local and requires a minimal number of assumptions. The tensor voting framework combines these properties and provides a unified perceptual organization methodology applicable in situations that may seem heterogeneous initially. We show how several problems can be posed as the organization of the inputs into salient perceptual structures, which are inferred via tensor voting. The work presented here extends the original tensor voting framework with the addition of boundary inference capabilities; a novel re-formulation of the framework applicable to high-dimensional spaces and the development of algorithms for computer vision and machine learning problems. We show complete analysis for some problems, while we briefly outline our approach for other applications and provide pointers to relevant sources.
650 0 $a Engineering. $3 162510
650 0 $a Electrical engineering. $3 191626
650 0 $a Signal processing. $3 148094
650 1 4 $a Technology and Engineering. $3 1000149430
650 2 4 $a Electrical and Electronic Engineering. $3 1000149431
650 2 4 $a Signal, Speech and Image Processing . $3 1000149489
700 1 $a Medioni, Gérard. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1000149570
710 2 $a SpringerLink (Online service) $3 1000143549
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783031011146
776 0 8 $i Printed edition: $z 9783031033704
830 0 $a Synthesis Lectures on Image, Video, and Multimedia Processing, $x 1559-8144 $3 1000149488
856 4 0 $u https://doi.org/10.1007/978-3-031-02242-5 $z Fulltext (查閱電子書全文)
912 $a ZDB-2-SXSC
950 $a Synthesis Collection of Technology (R0) (SpringerNature-85007)