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

Data Synthesis for Object Recognition.

Zhang, Xi.

Linked to FindBook

Google Book

Amazon

博客來

Data Synthesis for Object Recognition.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Data Synthesis for Object Recognition./
Author:	Zhang, Xi.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
Description:	140 p.
Notes:	Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
Contained By:	Dissertation Abstracts International79-08B(E).
Subject:	Computer science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10642437
ISBN:	9780355753325

Data Synthesis for Object Recognition.
Zhang, Xi.

Data Synthesis for Object Recognition. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 140 p.

Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.

Thesis (Ph.D.)--Illinois Institute of Technology, 2017.

Large and balanced datasets are normally crucial for many machine learning models, especially when the problem is defined in a high dimensional space due to high complexity. In real-world applications, it is usually very hard and/or expensive to obtain adequate amounts of labeled data, even with the help of crowd-sourcing. To address these problems, a possible approach is to create synthetic data and use it for training. This approach has been applied in many application areas of computer vision including document recognition, object retrieval, and object classification. While a boosted performance has been demonstrated using synthetic data, the boosted performance is limited by two main factors in existing approaches. First, most existing approaches for creating and using synthetic data are application-specific and thus lack the ability to benefit other application areas. Further, such application-specific approaches are often heuristic in nature. Second, existing approaches do not recognize an inherent difference between synthetic data and actual data which is termed as a synthetic gap in my proposal. The synthetic gap in existing approaches is due to the fact that not all possible patterns and structures of actual data are present in the synthetic data. To address the problems of using synthetic data and using it to better improve the performance of learning algorithm, this proposal considers general ways of creating and using synthetic data. The problem caused by the synthetic gap is studied and approaches to overcome the gap are proposed. Experimental results demonstrate that the proposed approach is efficient and can boost the performance of many computer vision applications including building roof classification, character classification, and point cloud object classification.

ISBN: 9780355753325Subjects--Topical Terms:

523869
Computer science.

Data Synthesis for Object Recognition.
LDR:02703nmm a2200289 4500 001 2160819
005 20180727125213.5
008 190424s2017 ||||||||||||||||| ||eng d
020 $a 9780355753325
035 $a (MiAaPQ)AAI10642437
035 $a (MiAaPQ)iit:10683
035 $a AAI10642437
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhang, Xi. $3 1256056
245 1 0 $a Data Synthesis for Object Recognition.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 140 p.
500 $a Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
500 $a Adviser: Gady Agam.
502 $a Thesis (Ph.D.)--Illinois Institute of Technology, 2017.
520 $a Large and balanced datasets are normally crucial for many machine learning models, especially when the problem is defined in a high dimensional space due to high complexity. In real-world applications, it is usually very hard and/or expensive to obtain adequate amounts of labeled data, even with the help of crowd-sourcing. To address these problems, a possible approach is to create synthetic data and use it for training. This approach has been applied in many application areas of computer vision including document recognition, object retrieval, and object classification. While a boosted performance has been demonstrated using synthetic data, the boosted performance is limited by two main factors in existing approaches. First, most existing approaches for creating and using synthetic data are application-specific and thus lack the ability to benefit other application areas. Further, such application-specific approaches are often heuristic in nature. Second, existing approaches do not recognize an inherent difference between synthetic data and actual data which is termed as a synthetic gap in my proposal. The synthetic gap in existing approaches is due to the fact that not all possible patterns and structures of actual data are present in the synthetic data. To address the problems of using synthetic data and using it to better improve the performance of learning algorithm, this proposal considers general ways of creating and using synthetic data. The problem caused by the synthetic gap is studied and approaches to overcome the gap are proposed. Experimental results demonstrate that the proposed approach is efficient and can boost the performance of many computer vision applications including building roof classification, character classification, and point cloud object classification.
590 $a School code: 0091.
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a Illinois Institute of Technology. $b Computer Science. $3 2094784
773 0 $t Dissertation Abstracts International $g 79-08B(E).
790 $a 0091
791 $a Ph.D.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10642437