
handle: 11449/237099
O trabalho desenvolvido traz um estudo sobre o agrupamento de imagens tridimensionais por meio da Análise Topológica de Dados (TDA). Nos primeiros capítulos, as principais definições da Topologia Algébrica são apresentadas para construção e entendimento dos cálculos realizados posteriormente. À seguir, são desenvolvidos programas na linguagem computacional Python para o estudo das mais de cento e cinquenta imagens, de vinte categorias distintas. Os agrupamentos foram realizados segundo a distância entre diagramas de persistência e imagens de persistência. As análises finais foram realizadas por meio de escalonamento multidimensional, dendrogramas e algoritmo k-means.
The work developed brings a study on the clustering of three-dimensional images through the Topological Data Analysis (TDA). In the first chapters, the main definitions of Algebraic Topology are presented for the construction and understanding of the calculations performed later. Next, programs are developed in the computer language Python for the study of more than one hundred and fifty images, from twenty different categories. Groupings were performed according to the distance between persistence diagrams and persistence images. Final analyses were performed using multidimensional scaling, dendrograms, and the k-means algorithm.
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
Pós-graduação em Matemática - IBILCE
CNPq: 132281/2021-1
Diagrama de persistência, Topological data analysis, Agrupamento, Persistence diagram, Topologia, Topology, Clustering, Análise topológica de dados
Diagrama de persistência, Topological data analysis, Agrupamento, Persistence diagram, Topologia, Topology, Clustering, Análise topológica de dados
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
