On the evaluation of photometric stereo applications testing using image modifications

Franz Wotawa; Ledio Jehaj; Nicole Brosch

doi:10.1007/978-3-031-43240-8_3

On the evaluation of photometric stereo applications testing using image modifications

Franz Wotawa (Speaker), Ledio Jehaj, Nicole Brosch

High-Performance Vision Systems

Graz University of Technology

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

Abstract

Computer vision is vital for various applications like object tracking for autonomous driving or quality assurance. Hence, assuring that computer vision fulfills given quality criteria is essential and requires sufficient testing. In previous work, authors introduced a testing method relying on image modifications for a photometric stereo application. Image modifications include pixel errors or the rotation of images to be analyzed, revealing a substantial impact on the computed outcome of the photometric stereo application, depending on the applied modification. This paper focuses on whether we can reproduce the impact of image modifications in a real-world setup. In particular, we compare the impact of the rotation of the analyzed sample with the rotation modification applied to the image of the sample. The comparison indicates a similar effect when using rotation, showing that testing based on image modifications is valuable for verifying computer vision applications.

Original language	English
Title of host publication	ICTSS 2023: Testing Software and Systems
Editors	S. Bonfanti, A. Gargantini, P. Salvaneschi
Pages	40-51
Number of pages	12
Volume	14131
ISBN (Electronic)	978-3-031-43240-8
DOIs	https://doi.org/10.1007/978-3-031-43240-8_3
Publication status	Published - 19 Sept 2023
Event	ICTSS 2023 : The 34th IFIP International Conference on Testing Software and Systems - Bergamo, Italy Duration: 18 Sept 2023 → 20 Sept 2023

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer, Cham
Volume	14131
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	ICTSS 2023 : The 34th IFIP International Conference on Testing Software and Systems
Abbreviated title	ICTS 2023
Country/Territory	Italy
City	Bergamo
Period	18/09/23 → 20/09/23

Research Field

High-Performance Vision Systems

Keywords

Testing computer vision applications
Test automation
Test case generation

Access to Document

10.1007/978-3-031-43240-8_3

1 Article

Evaluating Testing and Use of Photometric Stereo Applications for Riblet Inspection
Wotawa, F., Jahaj, L. & Brosch, N., 16 Dec 2024, In: SN Computer Science. 6, 2, p. 1 16 p.
Research output: Contribution to journal › Article › peer-review

Open Access

Cite this

@inproceedings{8561cda30a7c47f09f97ced585d67339,

title = "On the evaluation of photometric stereo applications testing using image modifications",

abstract = "Computer vision is vital for various applications like object tracking for autonomous driving or quality assurance. Hence, assuring that computer vision fulfills given quality criteria is essential and requires sufficient testing. In previous work, authors introduced a testing method relying on image modifications for a photometric stereo application. Image modifications include pixel errors or the rotation of images to be analyzed, revealing a substantial impact on the computed outcome of the photometric stereo application, depending on the applied modification. This paper focuses on whether we can reproduce the impact of image modifications in a real-world setup. In particular, we compare the impact of the rotation of the analyzed sample with the rotation modification applied to the image of the sample. The comparison indicates a similar effect when using rotation, showing that testing based on image modifications is valuable for verifying computer vision applications.",

keywords = "Testing computer vision applications, Test automation, Test case generation",

author = "Franz Wotawa and Ledio Jehaj and Nicole Brosch",

year = "2023",

month = sep,

day = "19",

doi = "10.1007/978-3-031-43240-8_3",

language = "English",

isbn = "978-3-031-43239-2",

volume = "14131",

series = "Lecture Notes in Computer Science",

publisher = "Springer, Cham",

pages = "40--51",

editor = "S. Bonfanti and A. Gargantini and P. Salvaneschi",

booktitle = "ICTSS 2023: Testing Software and Systems",

note = "ICTSS 2023 : The 34th IFIP International Conference on Testing Software and Systems, ICTS 2023 ; Conference date: 18-09-2023 Through 20-09-2023",

}

Wotawa, F, Jehaj, L & Brosch, N 2023, On the evaluation of photometric stereo applications testing using image modifications. in S Bonfanti, A Gargantini & P Salvaneschi (eds), ICTSS 2023: Testing Software and Systems. vol. 14131, Lecture Notes in Computer Science, vol. 14131, pp. 40-51, ICTSS 2023 : The 34th IFIP International Conference on Testing Software and Systems, Bergamo, Italy, 18/09/23. https://doi.org/10.1007/978-3-031-43240-8_3

On the evaluation of photometric stereo applications testing using image modifications. / Wotawa, Franz (Speaker); Jehaj, Ledio; Brosch, Nicole.
ICTSS 2023: Testing Software and Systems. ed. / S. Bonfanti; A. Gargantini; P. Salvaneschi. Vol. 14131 2023. p. 40-51 (Lecture Notes in Computer Science; Vol. 14131).

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

TY - GEN

T1 - On the evaluation of photometric stereo applications testing using image modifications

AU - Jehaj, Ledio

AU - Brosch, Nicole

A2 - Wotawa, Franz

A2 - Bonfanti, S.

A2 - Gargantini, A.

A2 - Salvaneschi, P.

PY - 2023/9/19

Y1 - 2023/9/19

N2 - Computer vision is vital for various applications like object tracking for autonomous driving or quality assurance. Hence, assuring that computer vision fulfills given quality criteria is essential and requires sufficient testing. In previous work, authors introduced a testing method relying on image modifications for a photometric stereo application. Image modifications include pixel errors or the rotation of images to be analyzed, revealing a substantial impact on the computed outcome of the photometric stereo application, depending on the applied modification. This paper focuses on whether we can reproduce the impact of image modifications in a real-world setup. In particular, we compare the impact of the rotation of the analyzed sample with the rotation modification applied to the image of the sample. The comparison indicates a similar effect when using rotation, showing that testing based on image modifications is valuable for verifying computer vision applications.

AB - Computer vision is vital for various applications like object tracking for autonomous driving or quality assurance. Hence, assuring that computer vision fulfills given quality criteria is essential and requires sufficient testing. In previous work, authors introduced a testing method relying on image modifications for a photometric stereo application. Image modifications include pixel errors or the rotation of images to be analyzed, revealing a substantial impact on the computed outcome of the photometric stereo application, depending on the applied modification. This paper focuses on whether we can reproduce the impact of image modifications in a real-world setup. In particular, we compare the impact of the rotation of the analyzed sample with the rotation modification applied to the image of the sample. The comparison indicates a similar effect when using rotation, showing that testing based on image modifications is valuable for verifying computer vision applications.

KW - Testing computer vision applications

KW - Test automation

KW - Test case generation

U2 - 10.1007/978-3-031-43240-8_3

DO - 10.1007/978-3-031-43240-8_3

M3 - Conference Proceedings with Oral Presentation

SN - 978-3-031-43239-2

VL - 14131

T3 - Lecture Notes in Computer Science

SP - 40

EP - 51

BT - ICTSS 2023: Testing Software and Systems

T2 - ICTSS 2023 : The 34th IFIP International Conference on Testing Software and Systems

Y2 - 18 September 2023 through 20 September 2023

ER -

On the evaluation of photometric stereo applications testing using image modifications

Abstract

Publication series

Conference

Research Field

Keywords

Access to Document

Fingerprint

Research output

Evaluating Testing and Use of Photometric Stereo Applications for Riblet Inspection

Cite this