Ponencia
Refined Deep Learning for Digital Objects Recognition via Betti Invariants
Autor/es | Onchis, Darian M.
Istin, Codruta Real Jurado, Pedro |
Departamento | Universidad de Sevilla. Departamento de Matemática Aplicada I (ETSII) |
Fecha de publicación | 2019 |
Fecha de depósito | 2021-09-30 |
Publicado en |
|
ISBN/ISSN | 978-3-030-29887-6 0302-9743 |
Resumen | In this paper, we make use of the topological invariants of
2D images for an accelerated training and an improved recognition ability
of a deep learning neural network applied to digital image objects.
For our test ... In this paper, we make use of the topological invariants of 2D images for an accelerated training and an improved recognition ability of a deep learning neural network applied to digital image objects. For our test images, we generate the associated simplicial complexes and from them we compute the Betti numbers which for a 2D object are the number of connected components and the number of holes. These information are used for training the network according to the corresponding Betti number. Experiments on the MNIST databases are presented in support of the proposed method. |
Agencias financiadoras | European Union (UE). H2020 |
Identificador del proyecto | INFRAIA- 2016-1-730897 |
Cita | Onchis, D.M., Istin, C. y Real Jurado, P. (2019). Refined Deep Learning for Digital Objects Recognition via Betti Invariants. En CAIP 2019: 18th International Conference on Computer Analysis of Images and Patterns (613-621), Salerno, Italy: Springer. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
Refined Deep Learning for ... | 788.8Kb | [PDF] | Ver/ | |