Perceptions of Time: Determine the Time of an Analogue Watch using Computer Vision
2022 (English)In: 2022 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT), Institute of Electrical and Electronics Engineers (IEEE), 2022Conference paper, Published paper (Refereed)
Abstract [en]
This paper explores the problem of determining the time of an analogue wristwatch by developing two systems and conducting a comparative study. The first system uses OpenCV to find the watch hands and applies geometrical techniques to calculate the time. The second system uses Machine Learning by building a neural network to classify images in Tensorflow using a multi-labelling approach. The results show that in a set environment the geometric-based approach performs better than the Machine Learning model. The geometric system predicted time correctly with an accuracy of 80% whereas the best Machine Learning model only achieves 74%. Experiments show that the accuracy of the neural network model did increase when using data augmentation, however there was no significant improvement when adding synthetic data to our training set.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2022.
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mau:diva-59126DOI: 10.1109/gcaiot57150.2022.10019054ISBN: 979-8-3503-0984-3 (electronic)ISBN: 979-8-3503-0985-0 (print)OAI: oai:DiVA.org:mau-59126DiVA, id: diva2:1749166
Conference
2022 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT), 18-21 December 2022, Alamein New City, Egypt
2023-04-052023-04-052023-04-05Bibliographically approved