Probabilistic Inspection using Deep Probabilistic Segmentation

Rasmus Eckholdt Andersen, Evangelos Boukas

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

The use of modern computer vision for defect detection is not a new concept. However, in many inspection processes, it is difficult to quantify the severity of the defects. Specifically, in cases where the current process relies on subjective human quantification, it is difficult to produce ground truth data, since each expert has a unique and sometimes non-repeatable opinion and, hence, the ground truth annotation might differ across different experts. Instead of averaging over expert opinions, as done implicitly when training traditional deterministic models, in this paper, we employ a Probabilistic U - Net to capture the hidden distribution of the subjective expert assessments. We investigate sampling the predicted expert distribution with a tiling approach down to a pixel level instead of on a per-image basis as originally proposed. We show that this sampling strategy does not affect the model's ability to represent the expert distribution. We evaluate the model's ability to converge by measuring the sum of absolute difference in means as more samples are added for each pixel. Our results show that sampling on a pixel level has the advantageous property of making the average over multiple samples converge towards a stable mean in a less fluctuating fashion thus making the model less sensitive to outliers, which makes it easier to decide on a final sample size.
Original languageEnglish
Title of host publicationProceedings of 2022 IEEE International Conference on Imaging Systems and Techniques
Number of pages6
PublisherIEEE
Publication date2022
ISBN (Print)9781665481021
DOIs
Publication statusPublished - 2022
Event2022 IEEE International Conference on Imaging Systems and Techniques - Virtual Event
Duration: 21 Jun 202223 Jun 2022
https://ist2022.ieee-ims.org/

Conference

Conference2022 IEEE International Conference on Imaging Systems and Techniques
LocationVirtual Event
Period21/06/202223/06/2022
Internet address

Keywords

  • Machine Learning
  • Corrosion detection
  • Variational Auto-Encoder

Fingerprint

Dive into the research topics of 'Probabilistic Inspection using Deep Probabilistic Segmentation'. Together they form a unique fingerprint.

Cite this