A CNN Model for Phytoplankton Classification in the Gulf of Venice

The study of plankton in the seas is crucial for the preservation of the marine ecosystem. In recent years, the application of advanced machine learning and deep learning techniques has significantly improved the classification of organisms in the seas. In this thesis, we will present a general overview of plankton image classification using machine learning and deep learning models, with a focus on convolutional neural networks (CNNs) and their application in phytoplankton classification in the Gulf of Venice. Furthermore, we will explore quantization techniques aimed to reduce the computational complexity of the models, making them executable on simpler hardware. Finally, we will analyze the results obtained using a VGG architecture and compare them with the current state of the art.