Print Email Facebook Twitter Analysing visual biases in coral imagery for bleaching detection Title Analysing visual biases in coral imagery for bleaching detection Author Vlekke, Jimmy (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Reinders, M.J.T. (mentor) Pintea, S. (graduation committee) Degree granting institution Delft University of Technology Date 2022-12-15 Abstract Global warming causes coral bleaching which threatens the health and existence of coral reefs and therefore also the future of a lot of species, including human beings. Efforts to automate coral reef monitoring using annotated coral images to detect coral bleaching are hindered by the lack of a complete dataset that specifies the health and bleaching status of corals. We propose to combine publicly available data into a dataset and train a CNN for coral bleaching detection. This model performs surprisingly well. However, combining data from different sources gives rise to dataset biases which helps classifiers perform better and make them unreliable for unseen data. We try to detect such biases and document themsing several bias detection methods. Subject Bias DetectionDataset biascoral bleachingCoral bleaching detectionCNNDeep Learning To reference this document use: http://resolver.tudelft.nl/uuid:4e649218-ac7b-4f78-b57e-5d1e4ed4fbcd Part of collection Student theses Document type master thesis Rights © 2022 Jimmy Vlekke Files PDF MSc_Thesis_Jimmy_Vlekke.pdf 39.13 MB Close viewer /islandora/object/uuid:4e649218-ac7b-4f78-b57e-5d1e4ed4fbcd/datastream/OBJ/view