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

Tensor voting for salient feature in...

University of Southern California.

Linked to FindBook

Google Book

Amazon

博客來

Tensor voting for salient feature inference in computer vision.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Tensor voting for salient feature inference in computer vision./
Author:	Lee, Mi-Suen.
Description:	127 p.
Notes:	Adviser: Gerard Medioni.
Contained By:	Dissertation Abstracts International60-02B.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9919071
ISBN:	9780599181250

Tensor voting for salient feature inference in computer vision.
Lee, Mi-Suen.

Tensor voting for salient feature inference in computer vision. - 127 p.

Adviser: Gerard Medioni.

Thesis (Ph.D.)--University of Southern California, 1998.

In computer vision, we often face the problem of extracting salient and structured information from a noisy data set. As computer vision systems move from controlled laboratory settings to real applications, the need for robust techniques to perform the inference of such salient structures becomes more apparent. For a salient structure estimator to be useful in computer vision, it must handle the presence of multiple structures, and the interaction between them, in noisy, irregularly clustered data sets. The derivation of such an estimator relies on the proper implementation of constraints, particularly the continuity constraint.

ISBN: 9780599181250Subjects--Topical Terms:

626642
Computer Science.

Tensor voting for salient feature inference in computer vision.
LDR:02898nmm 2200301 a 45 001 865777
005 20100729
008 100729s1998 ||||||||||||||||| ||eng d
020 $a 9780599181250
035 $a (UMI)AAI9919071
035 $a AAI9919071
040 $a UMI $c UMI
100 1 $a Lee, Mi-Suen. $3 1034228
245 1 0 $a Tensor voting for salient feature inference in computer vision.
300 $a 127 p.
500 $a Adviser: Gerard Medioni.
500 $a Source: Dissertation Abstracts International, Volume: 60-02, Section: B, page: 0716.
502 $a Thesis (Ph.D.)--University of Southern California, 1998.
520 $a In computer vision, we often face the problem of extracting salient and structured information from a noisy data set. As computer vision systems move from controlled laboratory settings to real applications, the need for robust techniques to perform the inference of such salient structures becomes more apparent. For a salient structure estimator to be useful in computer vision, it must handle the presence of multiple structures, and the interaction between them, in noisy, irregularly clustered data sets. The derivation of such an estimator relies on the proper implementation of constraints, particularly the continuity constraint.
520 $a We present a unified computational framework that makes use of the continuity constraint to generate descriptions in terms of surface, regions, curves, and labelled junctions, from sparse, noisy, binary data in 2-D or 3-D. Each input site can be a point, a point with an associated tangent direction, a point with an associated tangent vector, or any combination of the above. The methodology is grounded on two elements: tensor calculus for representation, and non-linear voting for communication: each input site communicates its information (a tensor) to its neighborhood through a predefined (tensor) field, and therefore casts a (tensor) vote. Each site collects all the votes cast at its location and encodes them into a new tensor. A local, parallel routine such as a modified marching squares process then simultaneously detects junctions, curves and region boundaries. The proposed approach is very different from traditional variational approaches, as it is non-iterative. Furthermore, the only free parameter is the size of the neighborhood, related to the scale.
520 $a We have developed several algorithms based on the proposed methodology to address a number of early vision problems, including perceptual grouping in 2-D and 3-D, shape from stereo, shape from shading, and motion grouping and segmentation, and the results are very encouraging.
590 $a School code: 0208.
650 4 $a Computer Science. $3 626642
650 4 $a Engineering, Electronics and Electrical. $3 626636
690 $a 0544
690 $a 0984
710 2 $a University of Southern California. $3 700129
773 0 $t Dissertation Abstracts International $g 60-02B.
790 $a 0208
790 1 0 $a Medioni, Gerard, $e advisor
791 $a Ph.D.
792 $a 1998
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=9919071