新生學校財團法人新生醫護管理專科學校圖書館 |

A computational framework for segmentation and grouping

Record Type:	Electronic resources : Monograph/item
Title/Author:	A computational framework for segmentation and grouping/ G�erard Medioni, Mi-Suen Lee, Chi-Keung Tang.
Author:	Medioni, G�erard.
other author:	Lee, Mi-Suen.
Published:	Amsterdam ;Elsevier, : 2000.,
Description:	xvi, 260 p. :ill. (some col.) ; : 27 cm. +; 1 computer disk (3 1/2 in.) +
Subject:	Computer vision. -
Online resource:	An electronic book accessible through the World Wide Web; click for information
ISBN:	9780444503534

A computational framework for segmentation and grouping
Medioni, G�erard.

A computational framework for segmentation and grouping[electronic resource] /G�erard Medioni, Mi-Suen Lee, Chi-Keung Tang. - Amsterdam ;Elsevier,2000. - xvi, 260 p. :ill. (some col.) ;27 cm. +1 computer disk (3 1/2 in.)

Includes bibliographical references and index.

This book represents a summary of the research we have been conducting since the early 1990s, and describes a conceptual framework which addresses some current shortcomings, and proposes a unified approach for a broad class of problems. While the framework is defined, our research continues, and some of the elements presented here will no doubt evolve in the coming years.It is organized in eight chapters. In the Introduction chapter, we present the definition of the problems, and give an overview of the proposed approach and its implementation. In particular, we illustrate the limitations of the 2.5D sketch, and motivate the use of a representation in terms of layers instead. In chapter 2, we review some of the relevant research in the literature. The discussion focuses on general computational approaches for early vision, and individual methods are only cited as references. Chapter 3 is the fundamental chapter, as it presents the elements of our salient feature inference engine, and their interaction. It introduced tensors as a way to represent information, tensor fields as a way to encode both constraints and results, and tensor voting as the communication scheme. Chapter 4 describes the feature extraction steps, given the computations performed by the engine described earlier. In chapter 5, we apply the generic framework to the inference of regions, curves, and junctions in 2-D. The input may take the form of 2-D points, with or without orientation. We illustrate the approach on a number of examples, both basic and advanced. In chapter 6, we apply the framework to the inference of surfaces, curves and junctions in 3-D. Here, the input consists of a set of 3-D points, with or without as associated normal or tangent direction. We show a number of illustrative examples, and also point to some applications of the approach. In chapter 7, we use our framework to tackle 3 early vision problems, shape from shading, stereo matching, and optical flow computation. In chapter 8, we conclude this book with a few remarks, and discuss future research directions. We include 3 appendices, one on Tensor Calculus, one dealing with proofs and details of the Feature Extraction process, and one dealing with the companion software packages.

Electronic reproduction.
Amsterdam :
Elsevier Science & Technology,
2007.

Mode of access: World Wide Web.

ISBN: 9780444503534

Source: 120927:127729Elsevier Science & Technologyhttp://www.sciencedirect.comSubjects--Topical Terms:

120994
Computer vision.
Index Terms--Genre/Form:

96803
Electronic books.

LC Class. No.: TA1634 / .M43 2000eb

Dewey Class. No.: 006.3/7

A computational framework for segmentation and grouping
LDR:04038cmm 2200349Ia 4500 001 152915
003 OCoLC
005 20100729101520.0
006 m d
007 cr cn|||||||||
008 160218s2000 ne a ob 001 0 eng d
020 $a 9780444503534
020 $a 0444503536
029 1 $a NZ1 $b 12435095
035 $a (OCoLC)162578272
035 $a ocn162578272
037 $a 120927:127729 $b Elsevier Science & Technology $n http://www.sciencedirect.com
040 $a OPELS $c OPELS
049 $a TEFA
050 1 4 $a TA1634 $b .M43 2000eb
072 7 $a QA $2 lcco
082 0 4 $a 006.3/7 $2 22
100 1 $a Medioni, G�erard. $3 290722
245 1 2 $a A computational framework for segmentation and grouping $h [electronic resource] / $c G�erard Medioni, Mi-Suen Lee, Chi-Keung Tang.
260 $a Amsterdam ; $a New York : $c 2000. $b Elsevier,
300 $a xvi, 260 p. : $b ill. (some col.) ; $c 27 cm. + $e 1 computer disk (3 1/2 in.)
504 $a Includes bibliographical references and index.
520 $a This book represents a summary of the research we have been conducting since the early 1990s, and describes a conceptual framework which addresses some current shortcomings, and proposes a unified approach for a broad class of problems. While the framework is defined, our research continues, and some of the elements presented here will no doubt evolve in the coming years.It is organized in eight chapters. In the Introduction chapter, we present the definition of the problems, and give an overview of the proposed approach and its implementation. In particular, we illustrate the limitations of the 2.5D sketch, and motivate the use of a representation in terms of layers instead. In chapter 2, we review some of the relevant research in the literature. The discussion focuses on general computational approaches for early vision, and individual methods are only cited as references. Chapter 3 is the fundamental chapter, as it presents the elements of our salient feature inference engine, and their interaction. It introduced tensors as a way to represent information, tensor fields as a way to encode both constraints and results, and tensor voting as the communication scheme. Chapter 4 describes the feature extraction steps, given the computations performed by the engine described earlier. In chapter 5, we apply the generic framework to the inference of regions, curves, and junctions in 2-D. The input may take the form of 2-D points, with or without orientation. We illustrate the approach on a number of examples, both basic and advanced. In chapter 6, we apply the framework to the inference of surfaces, curves and junctions in 3-D. Here, the input consists of a set of 3-D points, with or without as associated normal or tangent direction. We show a number of illustrative examples, and also point to some applications of the approach. In chapter 7, we use our framework to tackle 3 early vision problems, shape from shading, stereo matching, and optical flow computation. In chapter 8, we conclude this book with a few remarks, and discuss future research directions. We include 3 appendices, one on Tensor Calculus, one dealing with proofs and details of the Feature Extraction process, and one dealing with the companion software packages.
533 $a Electronic reproduction. $b Amsterdam : $c Elsevier Science & Technology, $d 2007. $n Mode of access: World Wide Web. $n System requirements: Web browser. $n Title from title screen (viewed on Aug. 2, 2007). $n Access may be restricted to users at subscribing institutions.
650 0 $a Computer vision. $3 120994
650 0 $a Calculus of tensors. $3 263326
650 6 $a Vision par ordinateur. $3 290725
650 6 $a Calcul tensoriel. $3 290726
655 7 $a Electronic books. $2 local. $3 96803
700 1 $a Lee, Mi-Suen. $3 290723
700 1 $a Tang, Chi-Keung. $3 290724
710 2 $a ScienceDirect (Online service) $3 254709
776 1 $c Original $z 0444503536 $z 9780444503534 $w (DLC) 00023205 $w (OCoLC)43481750
856 4 0 $3 ScienceDirect $u http://www.sciencedirect.com/science/book/9780444503534 $z An electronic book accessible through the World Wide Web; click for information
856 4 0 $3 Referex $u http://www.engineeringvillage.com/controller/servlet/OpenURL?genre=book&isbn=9780444503534 $z An electronic book accessible through the World Wide Web; click for information
856 4 2 $3 Publisher description $u http://www.loc.gov/catdir/enhancements/fy0609/00023205-d.html
994 $a C0 $b TEF