Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/132286
Title: Exploración de Vision Transformer para la clasificación de células normales de sangre periférica
Author: Ryba Maciejewska, Belén
Tutor: Alférez, Santiago  
Others: Calvet Liñán, Laura  
Abstract: Although Convolutional Neuronal Networks have revolutionized the world of computer vision,with the increasing size of datasets and the continuous development of new techniques, these models are beginning to present limitations, especially due to their high processing time. The following work analyzes Vision Transformer, a new proposed architecture that would allow overcoming these restrictions. Focusing its application in the field of computer science for the automatic recognition of cells in peripheral blood. The results obtained, with a higher classification accuracy than 0.96, show that ViT-based models are a promising alternative to the well-known CNN-based models for the performance of this type of tasks. In addition, a simple graphical interface is implemented with the aim of bringing users closer to the use of this type of algorithms for classification tasks, without any deep computer knowledge.
Keywords: Visual Transformer
deep learning
image classification
Document type: info:eu-repo/semantics/masterThesis
Issue Date: Jun-2021
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Trabajos finales de carrera, trabajos de investigación, etc.

Files in This Item:
File Description SizeFormat 
brybaTFM0621memoria.pdfMemoria del TFM2,51 MBAdobe PDFThumbnail
View/Open