Personal tools
You are here: Home News Classifying Plankton Species with Computer Vision and Deep Learning - Scott Lowe ANC

Classifying Plankton Species with Computer Vision and Deep Learning - Scott Lowe ANC

Kaggle competition


Scott Lowe entered a recent Kaggle competition "Predict ocean health, one plankton at a time", in which he competed  alongside a team of students from the School of Informatics.

The goal of the competition was using machine learning techniques to classify plankton species based on images collected from automated underwater microscopy. Scott's team placed 57th out of 1049 teams (top 5%).  Their solution used convolutional neural networks, hierarchical modelling, and feature-based computer vision methods.

See http://www.kaggle.com/c/datasciencebowl for details of the competition.