Sevillano Plaza, Victor2024-05-202024-05-202019-09-19https://hdl.handle.net/20.500.14468/14521In palynology, the visual classication of pollen grains from dierent species is a hard task which is usually tackled by human operators using microscopes. Its complete automatization would save a high quantity of resources and provide valuable improvements especially for allergy-related information systems, but also for other application elds as paleoclimate reconstruction, quality control of honey-based products, collection of evi- dences in criminal investigations or fabric dating and tracking. This paper presents three state-of-the-art deep learning classication methods applied to the recently published POLEN23E image dataset. The three methods make use of convolutional neural networks: the rst one is strictly based on the idea of transfer learning, the second one is based on feature extraction and the third one represents a hybrid approach, combining transfer learning and feature extraction. The results from the three methods are indeed very good, reaching over 99% correct classication rates in the training set of images and over 96% in images not previously seen by the models where other authors reported around 70%.eninfo:eu-repo/semantics/openAccesstesis de maestría