國立虎尾科技大學 |

Language: English

Back

Advanced Image Classification Using ...

ProQuest Information and Learning Co.

Advanced Image Classification Using Deep Neural Networks.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Advanced Image Classification Using Deep Neural Networks./
Author:	Williams, Travis Lamar.
Description:	1 online resource (164 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 79-07(E), Section: B.
Contained By:	Dissertation Abstracts International79-07B(E).
Subject:	Artificial intelligence. -
Online resource:	click for full text (PQDT)
ISBN:	9780355676716

Advanced Image Classification Using Deep Neural Networks.
Williams, Travis Lamar.

Advanced Image Classification Using Deep Neural Networks. - 1 online resource (164 pages)

Source: Dissertation Abstracts International, Volume: 79-07(E), Section: B.

Thesis (Ph.D.)--North Carolina Agricultural and Technical State University, 2017.

Includes bibliographical references

Image denoising and classification are two powerful sub-branches of image processing, due to their need in a wide range of fields and spheres of influence. The ubiquitous nature of pervasive computing technology currently intertwines itself with almost all forms of social media, and is increasingly becoming a normalized phenomenon in everyday life. Given this marriage of two technologies in high demand, the need for fast and accurate classification processes is insatiable. By joining deep learning algorithms with wavelet domain operations, the possibilities are abundant in discovering improvements and modifications to existing algorithms. For image classification, Convolutional Neural Networks is a state-of-the-art deep learning algorithm fit to classify two-dimensional images and objects. Despite its strengths, this algorithm welcomes renovations and upgrades for the furtherance of technological advances. Contributions and alternatives to the pooling layer, network regularization, and multiresolution level CNN-Wavelet networks are explored and theorized in this thesis.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355676716Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

Advanced Image Classification Using Deep Neural Networks.
LDR:02325ntm a2200337Ki 4500 001 916828
005 20180928111501.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355676716
035 $a (MiAaPQ)AAI10641349
035 $a (MiAaPQ)ncat:10810
035 $a AAI10641349
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Williams, Travis Lamar. $3 1190676
245 1 0 $a Advanced Image Classification Using Deep Neural Networks.
264 0 $c 2017
300 $a 1 online resource (164 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-07(E), Section: B.
500 $a Adviser: Robert Li.
502 $a Thesis (Ph.D.)--North Carolina Agricultural and Technical State University, 2017.
504 $a Includes bibliographical references
520 $a Image denoising and classification are two powerful sub-branches of image processing, due to their need in a wide range of fields and spheres of influence. The ubiquitous nature of pervasive computing technology currently intertwines itself with almost all forms of social media, and is increasingly becoming a normalized phenomenon in everyday life. Given this marriage of two technologies in high demand, the need for fast and accurate classification processes is insatiable. By joining deep learning algorithms with wavelet domain operations, the possibilities are abundant in discovering improvements and modifications to existing algorithms. For image classification, Convolutional Neural Networks is a state-of-the-art deep learning algorithm fit to classify two-dimensional images and objects. Despite its strengths, this algorithm welcomes renovations and upgrades for the furtherance of technological advances. Contributions and alternatives to the pooling layer, network regularization, and multiresolution level CNN-Wavelet networks are explored and theorized in this thesis.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Electrical engineering. $3 596380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0544
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a North Carolina Agricultural and Technical State University. $b Electrical Engineering. $3 1190677
773 0 $t Dissertation Abstracts International $g 79-07B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10641349 $z click for full text (PQDT)

based on 0 review(s)

Multimedia

Reviews

Add a review and share your thoughts with other readers

Export

pickup library