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

A dynamic method to reduce the searc...

Zhu, Junmei.

Linked to FindBook

Google Book

Amazon

博客來

A dynamic method to reduce the search space for visual correspondence problems.

Record Type:	Electronic resources : Monograph/item
Title/Author:	A dynamic method to reduce the search space for visual correspondence problems./
Author:	Zhu, Junmei.
Description:	80 p.
Notes:	Source: Dissertation Abstracts International, Volume: 65-07, Section: B, page: 3557.
Contained By:	Dissertation Abstracts International65-07B.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3140584
ISBN:	0496877259

A dynamic method to reduce the search space for visual correspondence problems.
Zhu, Junmei.

A dynamic method to reduce the search space for visual correspondence problems. - 80 p.

Source: Dissertation Abstracts International, Volume: 65-07, Section: B, page: 3557.

Thesis (Ph.D.)--University of Southern California, 2004.

This dissertation presents a fast self-organizing system for solving the visual correspondence problem, the creation of a mapping between corresponding points in two images with variations in position, scale; orientation, and deformation. The starting point for our system is Dynamic Link Matching (DLM). Dynamic links are implemented as synapses with rapid plasticity that can switch under the control of signal correlations on a time scale of 100 milliseconds. The links serve to connect corresponding points in the two images, and they self-organize to form continuous one-to-one mappings. DLM can deal with relative shift and is robust against deformation. It presupposes no learning or specific circuit structures, letting it appear as a plausible basis for early post-natal vision. But DLM requires thousands of iterations so it is not a viable model for fast adult object recognition. Moreover, DLM seems not to be able to deal with transformations too big to be considered as a mere deformation.

ISBN: 0496877259Subjects--Topical Terms:

626642
Computer Science.

A dynamic method to reduce the search space for visual correspondence problems.
LDR:03090nmm 2200301 4500 001 1846715
005 20051103093540.5
008 130614s2004 eng d
020 $a 0496877259
035 $a (UnM)AAI3140584
035 $a AAI3140584
040 $a UnM $c UnM
100 1 $a Zhu, Junmei. $3 1934816
245 1 2 $a A dynamic method to reduce the search space for visual correspondence problems.
300 $a 80 p.
500 $a Source: Dissertation Abstracts International, Volume: 65-07, Section: B, page: 3557.
500 $a Adviser: Christoph von der Malsburg.
502 $a Thesis (Ph.D.)--University of Southern California, 2004.
520 $a This dissertation presents a fast self-organizing system for solving the visual correspondence problem, the creation of a mapping between corresponding points in two images with variations in position, scale; orientation, and deformation. The starting point for our system is Dynamic Link Matching (DLM). Dynamic links are implemented as synapses with rapid plasticity that can switch under the control of signal correlations on a time scale of 100 milliseconds. The links serve to connect corresponding points in the two images, and they self-organize to form continuous one-to-one mappings. DLM can deal with relative shift and is robust against deformation. It presupposes no learning or specific circuit structures, letting it appear as a plausible basis for early post-natal vision. But DLM requires thousands of iterations so it is not a viable model for fast adult object recognition. Moreover, DLM seems not to be able to deal with transformations too big to be considered as a mere deformation.
520 $a Our new implementation requires direct interactions between links. These interactions are modeled with the help of maplets, which stand for local groups of links that are consistent with each other in terms of transformation parameters (position, orientation and scale). Links and maplets form a cooperative dynamic system that has the ability to converge very quickly on globally consistent mappings. In this process, feature similarities between the two images favor the correct correspondences. Experiments show that a mapping can be formed in just a few iterations, irrespective of differences in scale and in-plane rotation. This speed is due to the long range and specificity of link-to-link connections.
520 $a We also show that maplets and their connections can be learned by generalized Hebbian plasticity from consistent mappings, presumably formed by classical DLM. In simple pilot experiments the maplets formed by learning closely resemble those previously designed manually. Associative learning of link-to-link connections promises to extend the current system to more general variations (involving, e.g., rotation in depth).
590 $a School code: 0208.
650 4 $a Computer Science. $3 626642
650 4 $a Biology, Neuroscience. $3 1017680
690 $a 0984
690 $a 0317
710 2 0 $a University of Southern California. $3 700129
773 0 $t Dissertation Abstracts International $g 65-07B.
790 1 0 $a von der Malsburg, Christoph, $e advisor
790 $a 0208
791 $a Ph.D.
792 $a 2004
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3140584