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

Shift Invariant Support Vector Machi...

Omoregbee, Ehimwenma.

Linked to FindBook

Google Book

Amazon

博客來

Shift Invariant Support Vector Machine for Image Classification in Automatic Target Recognition Systems.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Shift Invariant Support Vector Machine for Image Classification in Automatic Target Recognition Systems./
Author:	Omoregbee, Ehimwenma.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
Description:	182 p.
Notes:	Source: Masters Abstracts International, Volume: 84-11.
Contained By:	Masters Abstracts International84-11.
Subject:	Electrical engineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30423432
ISBN:	9798379572990

Shift Invariant Support Vector Machine for Image Classification in Automatic Target Recognition Systems.
Omoregbee, Ehimwenma.

Shift Invariant Support Vector Machine for Image Classification in Automatic Target Recognition Systems. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 182 p.

Source: Masters Abstracts International, Volume: 84-11.

Thesis (M.S.)--Tuskegee University, 2023.

This item must not be sold to any third party vendors.

Detection and classification of Synthetic Aperture Radar (SAR) targets are especially important in automatic target recognition (ATR) applications. ATR includes detecting, classifying, and identifying targets within a scene. There are several approaches to ATR, and expectedly, each class of algorithms has strengths and also, exhibits some weaknesses. In this thesis, the focus is on developing a novel algorithm that combines the concepts of distance classifier correlation filters(DCCF) and Support vector machines (SVMs) to achieve the best possible shift-invariant classification tailored to real-time scenarios. The DCCF framework will be used as the kernel of the SVM algorithm; that is, we use DCCF to develop a new kernel function to make the non-linearly separable input data separable. We will demonstrate that the proposed kernel satisfies Mercer's condition, a theoretical requirement for viable SVM kernels.Although not shift-invariant, SVM algorithms are well-known for classification and tend to generalize well for targets not contained in the training set. DCCF increases the distance of separation between classes while making each class more compact by minimizing the intra-class distance and maximizing the inter-class distance. The proposed algorithm will rely on the strengths of DCCF and SVM algorithms. Performance results are assessed by comparing the proposed algorithm to state-of-the-art shift invariant ATR algorithms such as Maximum margin correlation filters (MMCF), Unconstrained Minimum average correlation energy (UMACE), and Optimum tradeoff synthetic discriminant function (OTSDF).

ISBN: 9798379572990Subjects--Topical Terms:

649834
Electrical engineering.
Subjects--Index Terms:

Synthetic aperture radar

Shift Invariant Support Vector Machine for Image Classification in Automatic Target Recognition Systems.
LDR:02869nmm a2200397 4500 001 2395484
005 20240517104604.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798379572990
035 $a (MiAaPQ)AAI30423432
035 $a AAI30423432
040 $a MiAaPQ $c MiAaPQ
100 1 $a Omoregbee, Ehimwenma. $3 3764990
245 1 0 $a Shift Invariant Support Vector Machine for Image Classification in Automatic Target Recognition Systems.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 182 p.
500 $a Source: Masters Abstracts International, Volume: 84-11.
500 $a Advisor: Ndoye, Mandoye;Khan, Jesmin.
502 $a Thesis (M.S.)--Tuskegee University, 2023.
506 $a This item must not be sold to any third party vendors.
520 $a Detection and classification of Synthetic Aperture Radar (SAR) targets are especially important in automatic target recognition (ATR) applications. ATR includes detecting, classifying, and identifying targets within a scene. There are several approaches to ATR, and expectedly, each class of algorithms has strengths and also, exhibits some weaknesses. In this thesis, the focus is on developing a novel algorithm that combines the concepts of distance classifier correlation filters(DCCF) and Support vector machines (SVMs) to achieve the best possible shift-invariant classification tailored to real-time scenarios. The DCCF framework will be used as the kernel of the SVM algorithm; that is, we use DCCF to develop a new kernel function to make the non-linearly separable input data separable. We will demonstrate that the proposed kernel satisfies Mercer's condition, a theoretical requirement for viable SVM kernels.Although not shift-invariant, SVM algorithms are well-known for classification and tend to generalize well for targets not contained in the training set. DCCF increases the distance of separation between classes while making each class more compact by minimizing the intra-class distance and maximizing the inter-class distance. The proposed algorithm will rely on the strengths of DCCF and SVM algorithms. Performance results are assessed by comparing the proposed algorithm to state-of-the-art shift invariant ATR algorithms such as Maximum margin correlation filters (MMCF), Unconstrained Minimum average correlation energy (UMACE), and Optimum tradeoff synthetic discriminant function (OTSDF).
590 $a School code: 1193.
650 4 $a Electrical engineering. $3 649834
650 4 $a Remote sensing. $3 535394
650 4 $a Computer science. $3 523869
653 $a Synthetic aperture radar
653 $a SVM algorithms
653 $a Support vector machines
653 $a Automatic target recognition
653 $a Input data
690 $a 0544
690 $a 0984
690 $a 0799
710 2 $a Tuskegee University. $b College of Engineering. $3 3764991
773 0 $t Masters Abstracts International $g 84-11.
790 $a 1193
791 $a M.S.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30423432