國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

A detection-based pattern recognitio...

Georgia Institute of Technology.

A detection-based pattern recognition framework and its applications.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	A detection-based pattern recognition framework and its applications.
作者:	Ma, Chengyuan.
面頁冊數:	139 p.
附註:	Source: Dissertation Abstracts International, Volume: 71-07, Section: B, page: .
附註:	Adviser: Chin-Hui Lee.
Contained By:	Dissertation Abstracts International71-07B.
標題:	Engineering, Electronics and Electrical.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3414486
ISBN:	9781124076164

A detection-based pattern recognition framework and its applications.
Ma, Chengyuan.

A detection-based pattern recognition framework and its applications. - 139 p.

Source: Dissertation Abstracts International, Volume: 71-07, Section: B, page: .

Thesis (Ph.D.)--Georgia Institute of Technology, 2010.

The objective of this dissertation is to present a detection-based pattern recognition framework and demonstrate its applications in automatic speech recognition and broadcast news video story segmentation.

ISBN: 9781124076164Subjects--Topical Terms:

226981
Engineering, Electronics and Electrical.

A detection-based pattern recognition framework and its applications.
LDR:03185nmm 2200301 4500 001 280828
005 20110119095004.5
008 110301s2010 ||||||||||||||||| ||eng d
020 $a 9781124076164
035 $a (UMI)AAI3414486
035 $a AAI3414486
040 $a UMI $c UMI
100 1 $a Ma, Chengyuan. $3 492962
245 1 2 $a A detection-based pattern recognition framework and its applications.
300 $a 139 p.
500 $a Source: Dissertation Abstracts International, Volume: 71-07, Section: B, page: .
500 $a Adviser: Chin-Hui Lee.
502 $a Thesis (Ph.D.)--Georgia Institute of Technology, 2010.
520 $a The objective of this dissertation is to present a detection-based pattern recognition framework and demonstrate its applications in automatic speech recognition and broadcast news video story segmentation.
520 $a Inspired by the studies of modern cognitive psychology and real-world pattern recognition systems, a detection-based pattern recognition framework is proposed to provide an alternative solution for some complicated pattern recognition problems. The primitive features are first detected and the task-specific knowledge hierarchy is constructed level by level. Then, a variety of heterogeneous information sources are combined together and the high level context is incorporated as additional information at certain stages.
520 $a A detection-based framework is a "divide-and-conquer" design paradigm for pattern recognition problems, which will decomposes a conceptually difficult problem into many elementary subproblems that can be handled directly and reliably. Some information fusion strategies will be employed to integrate the evidence from a lower level to form the evidence at a higher level. Such a fusion procedure continues until reaching the top level. Generally, a detection-based framework has many advantages: (1) more flexibility in both detector design and fusion strategies, as these two parts can be optimized separately; (2) parallel and distributed computational components in primitive feature detection. In such a component-based framework, any primitive component can be replaced by a new one while other components remain unchanged; (3) incremental information integration; (4) high level context information as additional information sources, which can be combined with bottom-up processing at any stage.
520 $a This dissertation presents the basic principles, criteria, and techniques for detector design and hypothesis verification based on the statistical detection and decision theory. In addition, evidence fusion strategies were investigated in this dissertation. Several novel detection algorithms and evidence fusion methods were proposed and their effectiveness was justified in automatic speech recognition and broadcast news video segmentation system. We believe such a detection-based framework can be employed in more applications in the future.
590 $a School code: 0078.
650 4 $a Engineering, Electronics and Electrical. $3 226981
690 $a 0544
710 2 $a Georgia Institute of Technology. $3 212511
773 0 $t Dissertation Abstracts International $g 71-07B.
790 1 0 $a Lee, Chin-Hui, $e advisor
790 $a 0078
791 $a Ph.D.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3414486