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

Understanding Image Quality for Deep...

Bergstrom, Austin.

Linked to FindBook

Google Book

Amazon

博客來

Understanding Image Quality for Deep Learning-Based Computer Vision.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Understanding Image Quality for Deep Learning-Based Computer Vision./
Author:	Bergstrom, Austin.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
Description:	164 p.
Notes:	Source: Dissertations Abstracts International, Volume: 85-02, Section: B.
Contained By:	Dissertations Abstracts International85-02B.
Subject:	Systems science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30635067
ISBN:	9798380149402

Understanding Image Quality for Deep Learning-Based Computer Vision.
Bergstrom, Austin.

Understanding Image Quality for Deep Learning-Based Computer Vision. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 164 p.

Source: Dissertations Abstracts International, Volume: 85-02, Section: B.

Thesis (Ph.D.)--Rochester Institute of Technology, 2023.

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

Extensive research has gone into optimizing convolutional neural network (CNN) architectures for tasks such as image classification and object detection, but research to date on the relationship between input image quality and CNN prediction performance has been relatively limited. Additionally, while CNN generalization against out-of-distribution image distortions persists as a significant challenge and a focus of substantial research, a range of studies have suggested that CNNs can be be made robust to low visual quality images when the distortions are predictable. In this research, we systematically study the relationships between image quality and CNN performance on image classification and detection tasks. We find that while generalization remains a significant challenge for CNNs faced with out-of-distribution image distortions, CNN performance against low visual quality images remains strong with appropriate training, indicating the potential to expand the design trade space for sensors providing data to computer vision systems. We find that the functional form of the GIQE can predict CNN performance as a function of image degradation, but we observe that the legacy form of the GIQE does a better job of modeling the impact of blur/relative edge response in some scenarios. Additionally, we evaluate other image quality models that lack the pedigree of the GIQE and find that they generally work as well or better than the functional form of the GIQE in modeling computer vision performance on distorted images. We observe that object detector performance is qualitatively very similar to image classifier performance in the presence of image distortion. Finally, we observe that computer vision performance tends to exhibit relatively smooth, monotonic variation with blur and noise, but we find that performance is relatively insensitive to resolution under a range of conditions.

ISBN: 9798380149402Subjects--Topical Terms:

3168411
Systems science.
Subjects--Index Terms:

Image quality

Understanding Image Quality for Deep Learning-Based Computer Vision.
LDR:03149nmm a2200397 4500 001 2395758
005 20240517105011.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798380149402
035 $a (MiAaPQ)AAI30635067
035 $a AAI30635067
040 $a MiAaPQ $c MiAaPQ
100 1 $a Bergstrom, Austin. $3 3765266
245 1 0 $a Understanding Image Quality for Deep Learning-Based Computer Vision.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 164 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-02, Section: B.
500 $a Advisor: Messinger, David.
502 $a Thesis (Ph.D.)--Rochester Institute of Technology, 2023.
506 $a This item must not be sold to any third party vendors.
520 $a Extensive research has gone into optimizing convolutional neural network (CNN) architectures for tasks such as image classification and object detection, but research to date on the relationship between input image quality and CNN prediction performance has been relatively limited. Additionally, while CNN generalization against out-of-distribution image distortions persists as a significant challenge and a focus of substantial research, a range of studies have suggested that CNNs can be be made robust to low visual quality images when the distortions are predictable. In this research, we systematically study the relationships between image quality and CNN performance on image classification and detection tasks. We find that while generalization remains a significant challenge for CNNs faced with out-of-distribution image distortions, CNN performance against low visual quality images remains strong with appropriate training, indicating the potential to expand the design trade space for sensors providing data to computer vision systems. We find that the functional form of the GIQE can predict CNN performance as a function of image degradation, but we observe that the legacy form of the GIQE does a better job of modeling the impact of blur/relative edge response in some scenarios. Additionally, we evaluate other image quality models that lack the pedigree of the GIQE and find that they generally work as well or better than the functional form of the GIQE in modeling computer vision performance on distorted images. We observe that object detector performance is qualitatively very similar to image classifier performance in the presence of image distortion. Finally, we observe that computer vision performance tends to exhibit relatively smooth, monotonic variation with blur and noise, but we find that performance is relatively insensitive to resolution under a range of conditions.
590 $a School code: 0465.
650 4 $a Systems science. $3 3168411
650 4 $a Information technology. $3 532993
653 $a Image quality
653 $a Deep learning
653 $a Computer vision
653 $a Convolutional neural network
653 $a Object detector performance
690 $a 0790
690 $a 0800
690 $a 0489
710 2 $a Rochester Institute of Technology. $b Imaging Science. $3 1019498
773 0 $t Dissertations Abstracts International $g 85-02B.
790 $a 0465
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30635067