Objective Construction of Ground Truth Images
Paper
Paper/Presentation Title | Objective Construction of Ground Truth Images |
---|---|
Presentation Type | Paper |
Authors | Smith, Mark (Author), Maiti, Ananda (Author), Maxwell, Andrew (Author) and Kist, Alexander A. (Author) |
Editors | Auer, Michael E. and May, Dominik |
Journal or Proceedings Title | Lecture Notes in Advances in Intelligent Systems and Computing (Book series) |
ERA Conference ID | 50808 |
Journal Citation | 1231, pp. 300-312 |
Number of Pages | 13 |
Year | 2021 |
Publisher | Springer |
Place of Publication | Switzerland |
ISSN | 2194-5357 |
2194-5365 | |
ISBN | 9783030525743 |
9783030525750 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-030-52575-0_24 |
Web Address (URL) of Paper | https://link.springer.com/book/10.1007/978-3-030-52575-0 |
Conference/Event | 17th International Conference on Remote Engineering and Virtual Instrumentation (REV 2020) |
International Conference on Remote Engineering and Virtual Instrumentation | |
Event Details | 17th International Conference on Remote Engineering and Virtual Instrumentation (REV 2020) Parent International Conference on Remote Engineering and Virtual Instrumentation Delivery In person Event Date 26 to end of 28 Feb 2020 Event Location Athens, United States |
Event Details | International Conference on Remote Engineering and Virtual Instrumentation REV |
Abstract | In the context of virtual and augmented reality, computer vision plays a pivotal role. To benchmark performance, evaluation of computer vision models, such as edge detection is essential. Traditionally this has relied on subjective analysis of the resultant images. Alternatively, models have been assessed against ground truth images. However, ground truth images are highly subjective, relying on human judging to determine the appropriate location of features. Literature complains about the lack of objective quantitative measures for model evaluation, yet no solution has been presented. Ground truth is the objective verification of properties of an image. In the context of this paper it is a data set that includes an accurate and complete representation of the edges. The subjective nature of creating ground truth images has meant that true image analysis model evaluation has been limited. Reducing the level of subjective decisions can improve the confidence level when measuring the performance of computer vision image analysis models. This work describes a new method to improve ground truth image confidence through an automated computer vision feature detection model voting system. |
Keywords | Computer vision; Edge detection; Ground truth |
ANZSRC Field of Research 2020 | 460306. Image processing |
460799. Graphics, augmented reality and games not elsewhere classified | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | School of Mechanical and Electrical Engineering |
University of Tasmania | |
Institution of Origin | University of Southern Queensland |
Book Title | Cross Reality and Data Science in Engineering. REV 2020. Advances in Intelligent Systems and Computing |
https://research.usq.edu.au/item/q71qq/objective-construction-of-ground-truth-images
122
total views5
total downloads3
views this month0
downloads this month