Analysing visual biases in coral imagery for bleaching detection

Analysing visual biases in coral imagery for bleaching detection

Vlekke, Jimmy (TU Delft Electrical Engineering, Mathematics and Computer Science)

Reinders, M.J.T. (mentor)
Pintea, S. (graduation committee)

Delft University of Technology

2022-12-15

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.

Bias Detection
Dataset bias
coral bleaching
Coral bleaching detection
CNN
Deep Learning

http://resolver.tudelft.nl/uuid:4e649218-ac7b-4f78-b57e-5d1e4ed4fbcd

Student theses

master thesis

© 2022 Jimmy Vlekke