Show simple item record  

dc.contributor.advisorBowen, Judy
dc.contributor.advisorOoi, Melanie Po-Leen
dc.contributor.advisorMayo, Michael
dc.contributor.advisorPatros, Panos
dc.contributor.authorHerbert, Callum
dc.date.accessioned2023-11-12T22:46:18Z
dc.date.available2023-11-12T22:46:18Z
dc.date.issued2023
dc.identifier.urihttps://hdl.handle.net/10289/16129
dc.description.abstractDeep learning based computer vision technologies can offer a number of advantages over manual labour inspection methods such as reduced operational costs and efficiency improvements. However, they are known to be unreliable in certain situations, especially when input images contain augmentations such as occlusion or distortion that computer vision models have not been trained on. While augmentations can be mitigated by controlling some situations, this is not always possible, especially in outdoor environments. To address this issue, one common approach is supplemental robustness training using augmented training data, which involves training models on images containing the expected augmentations to improve performance. However, this approach requires collection of a substantial volume of augmented images for each expected augmentation, making it time-consuming and costly depending on the difficulty involved in reproducing each augmentation. This thesis explores the viability of using artificially rendered augmentations on unaugmented images as a substitute for the manual collection and preparation of naturally augmented data for image recognition and object detection models. Specifically, this thesis recreates nine environmental augmentations that commonly occur within outdoor environments and evaluates their impact on model performance on three datasets. The findings of this thesis indicate potential for using artificially generated augmentations as substitutes for naturally occurring augmentations. It is anticipated that further research in this area will enable more reliable image recognition and object detection in less controllable environments, thus improving the results of these technologies in uncertain situations.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherThe University of Waikato
dc.rightsAll items in Research Commons are provided for private study and research purposes and are protected by copyright with all rights reserved unless otherwise indicated.
dc.subjectDeep learning
dc.subjectImage recognition
dc.subjectObject detection
dc.subjectImage augmentation
dc.subjectArtifical image generation
dc.subjectModel robustness
dc.subject.lcshImage processing
dc.subject.lcshPattern recognition systems
dc.subject.lcshPattern perception
dc.subject.lcshAugmented reality
dc.subject.lcshComputer vision
dc.subject.lcshDeep learning (Machine learning)
dc.titleImproving robustness of image recognition through artificial image augmentation
dc.typeThesis
thesis.degree.grantorThe University of Waikato
thesis.degree.levelMasters
thesis.degree.nameMaster of Engineering (ME)
dc.date.updated2023-11-09T21:20:35Z
pubs.place-of-publicationHamilton, New Zealanden_NZ


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record