Getting Crevices, Cracks, and Grooves in Line: Anomaly Categorization for AQC Judgment Models

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

The production of high-end manufactured products requires expensive human aesthetic quality control (AQC) in the form of e.g. visual inspection at multiple stages during production. Current standards for aesthetic quality control focus on the process, i.e. identifying the source of anomalies and lack an observer-oriented classification (describing the perceived appearance). We found a need for a perceptual categorization of anomalies that can help assessors making quality judgments and we present a judgment model for AQC. To this end, we studied visual inspection task flows, and processes especially around limit samples at Bang Olufsen. Based on perceptual responses in the human visual system, we propose a categorization consisting of open and closed shapes. The latter contains areas, lines, alignment, and constellations. The categorization can help in automating AQC using computer vision.

Original languageEnglish
Title of host publicationTenth International Conference on Quality of Multimedia Experience (QoMEX), 2018
Number of pages3
PublisherIEEE
Publication date11 Sep 2018
Article number8463295
DOIs
Publication statusPublished - 11 Sep 2018
EventTenth International Conference on Quality of Multimedia Experience (QoMEX), 2018 - Sardinia, Italy
Duration: 29 May 20181 Jun 2018

Conference

ConferenceTenth International Conference on Quality of Multimedia Experience (QoMEX), 2018
CountryItaly
CitySardinia
Period29/05/201801/06/2018
SeriesInternational Conference on Quality of Multimedia Experience (QoMEX)
ISSN2472-7814

Fingerprint

Quality control
Cracks
Inspection
Computer vision

Keywords

  • Aesthetic
  • judgment
  • quality
  • visual appearance

Cite this

Hansen, A. J., Knoche, H., & Moeslund, T. B. (2018). Getting Crevices, Cracks, and Grooves in Line: Anomaly Categorization for AQC Judgment Models. In Tenth International Conference on Quality of Multimedia Experience (QoMEX), 2018 [8463295] IEEE. International Conference on Quality of Multimedia Experience (QoMEX) https://doi.org/10.1109/QoMEX.2018.8463295
Hansen, Anne Juhler ; Knoche, Hendrik ; Moeslund, Thomas B. / Getting Crevices, Cracks, and Grooves in Line : Anomaly Categorization for AQC Judgment Models. Tenth International Conference on Quality of Multimedia Experience (QoMEX), 2018. IEEE, 2018. (International Conference on Quality of Multimedia Experience (QoMEX)).
@inproceedings{8c9da39c74c2418482e8ef495b8e9ef1,
title = "Getting Crevices, Cracks, and Grooves in Line: Anomaly Categorization for AQC Judgment Models",
abstract = "The production of high-end manufactured products requires expensive human aesthetic quality control (AQC) in the form of e.g. visual inspection at multiple stages during production. Current standards for aesthetic quality control focus on the process, i.e. identifying the source of anomalies and lack an observer-oriented classification (describing the perceived appearance). We found a need for a perceptual categorization of anomalies that can help assessors making quality judgments and we present a judgment model for AQC. To this end, we studied visual inspection task flows, and processes especially around limit samples at Bang Olufsen. Based on perceptual responses in the human visual system, we propose a categorization consisting of open and closed shapes. The latter contains areas, lines, alignment, and constellations. The categorization can help in automating AQC using computer vision.",
keywords = "Aesthetic, judgment, quality, visual appearance",
author = "Hansen, {Anne Juhler} and Hendrik Knoche and Moeslund, {Thomas B.}",
year = "2018",
month = "9",
day = "11",
doi = "10.1109/QoMEX.2018.8463295",
language = "English",
booktitle = "Tenth International Conference on Quality of Multimedia Experience (QoMEX), 2018",
publisher = "IEEE",
address = "United States",

}

Hansen, AJ, Knoche, H & Moeslund, TB 2018, Getting Crevices, Cracks, and Grooves in Line: Anomaly Categorization for AQC Judgment Models. in Tenth International Conference on Quality of Multimedia Experience (QoMEX), 2018., 8463295, IEEE, International Conference on Quality of Multimedia Experience (QoMEX), Tenth International Conference on Quality of Multimedia Experience (QoMEX), 2018 , Sardinia, Italy, 29/05/2018. https://doi.org/10.1109/QoMEX.2018.8463295

Getting Crevices, Cracks, and Grooves in Line : Anomaly Categorization for AQC Judgment Models. / Hansen, Anne Juhler; Knoche, Hendrik; Moeslund, Thomas B.

Tenth International Conference on Quality of Multimedia Experience (QoMEX), 2018. IEEE, 2018. 8463295.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Getting Crevices, Cracks, and Grooves in Line

T2 - Anomaly Categorization for AQC Judgment Models

AU - Hansen, Anne Juhler

AU - Knoche, Hendrik

AU - Moeslund, Thomas B.

PY - 2018/9/11

Y1 - 2018/9/11

N2 - The production of high-end manufactured products requires expensive human aesthetic quality control (AQC) in the form of e.g. visual inspection at multiple stages during production. Current standards for aesthetic quality control focus on the process, i.e. identifying the source of anomalies and lack an observer-oriented classification (describing the perceived appearance). We found a need for a perceptual categorization of anomalies that can help assessors making quality judgments and we present a judgment model for AQC. To this end, we studied visual inspection task flows, and processes especially around limit samples at Bang Olufsen. Based on perceptual responses in the human visual system, we propose a categorization consisting of open and closed shapes. The latter contains areas, lines, alignment, and constellations. The categorization can help in automating AQC using computer vision.

AB - The production of high-end manufactured products requires expensive human aesthetic quality control (AQC) in the form of e.g. visual inspection at multiple stages during production. Current standards for aesthetic quality control focus on the process, i.e. identifying the source of anomalies and lack an observer-oriented classification (describing the perceived appearance). We found a need for a perceptual categorization of anomalies that can help assessors making quality judgments and we present a judgment model for AQC. To this end, we studied visual inspection task flows, and processes especially around limit samples at Bang Olufsen. Based on perceptual responses in the human visual system, we propose a categorization consisting of open and closed shapes. The latter contains areas, lines, alignment, and constellations. The categorization can help in automating AQC using computer vision.

KW - Aesthetic

KW - judgment

KW - quality

KW - visual appearance

UR - http://www.scopus.com/inward/record.url?scp=85054416202&partnerID=8YFLogxK

U2 - 10.1109/QoMEX.2018.8463295

DO - 10.1109/QoMEX.2018.8463295

M3 - Article in proceeding

BT - Tenth International Conference on Quality of Multimedia Experience (QoMEX), 2018

PB - IEEE

ER -

Hansen AJ, Knoche H, Moeslund TB. Getting Crevices, Cracks, and Grooves in Line: Anomaly Categorization for AQC Judgment Models. In Tenth International Conference on Quality of Multimedia Experience (QoMEX), 2018. IEEE. 2018. 8463295. (International Conference on Quality of Multimedia Experience (QoMEX)). https://doi.org/10.1109/QoMEX.2018.8463295