國立虎尾科技大學 |

Understanding Image Quality for Deep Learning-Based Computer Vision.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Understanding Image Quality for Deep Learning-Based Computer Vision./
作者:	Bergstrom, Austin.
面頁冊數:	1 online resource (164 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-02, Section: B.
Contained By:	Dissertations Abstracts International85-02B.
標題:	Information technology. -
電子資源:	click for full text (PQDT)
ISBN:	9798380149402

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

Understanding Image Quality for Deep Learning-Based Computer Vision. - 1 online resource (164 pages)

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

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

Includes bibliographical references

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.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380149402Subjects--Topical Terms:

559429
Information technology.
Subjects--Index Terms:

Image qualityIndex Terms--Genre/Form:

554714
Electronic books.

Understanding Image Quality for Deep Learning-Based Computer Vision.
LDR:03302ntm a22003977 4500 001 1143854
005 20240517105011.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380149402
035 $a (MiAaPQ)AAI30635067
035 $a AAI30635067
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Bergstrom, Austin. $3 1468659
245 1 0 $a Understanding Image Quality for Deep Learning-Based Computer Vision.
264 0 $c 2023
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: Dissertations Abstracts International, Volume: 85-02, Section: B.
500 $a Advisor: Messinger, David.
502 $a Thesis (Ph.D.)--Rochester Institute of Technology, 2023.
504 $a Includes bibliographical references
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.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Information technology. $3 559429
650 4 $a Systems science. $3 1148479
653 $a Image quality
653 $a Deep learning
653 $a Computer vision
653 $a Convolutional neural network
653 $a Object detector performance
655 7 $a Electronic books. $2 local $3 554714
690 $a 0790
690 $a 0800
690 $a 0489
710 2 $a Rochester Institute of Technology. $b Imaging Science. $3 1187019
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Dissertations Abstracts International $g 85-02B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30635067 $z click for full text (PQDT)