Listar Dpto. Estadística, Informática y Matemáticas - Estatistika, Informatika eta Matematika Saila [desde mayo 2018 / 2018ko maiatzetik] por autor UPNA "Pagola Barrio, Miguel"
Mostrando ítems 1-5 de 5
-
Co-occurrence of deep convolutional features for image search
Forcén Carvalho, Juan Ignacio; Pagola Barrio, Miguel
; Barrenechea Tartas, Edurne ; Bustince Sola, Humberto (Elsevier, 2020)
Artículo / Artikulua 
Image search can be tackled using deep features from pre-trained Convolutional Neural Networks (CNN). The feature map from the last convolutional layer of a CNN encodes descriptive information from which a discriminative ... -
Image feature extraction using OD-monotone functions
Marco Detchart, Cedric ; López Molina, Carlos ; Fernández Fernández, Francisco Javier ; Pagola Barrio, Miguel ; Bustince Sola, Humberto (Springer, 2018)
Contribución a congreso / Biltzarrerako ekarpena
Edge detection is a basic technique used as a preliminary step for, e.g., object extraction and recognition in image processing. Many of the methods for edge detection can be fit in the breakdown structure by Bezdek, ... -
Learning ordered pooling weights in image classification
Forcén Carvalho, Juan Ignacio; Pagola Barrio, Miguel ; Barrenechea Tartas, Edurne ; Bustince Sola, Humberto (Elsevier, 2020)
Artículo / Artikulua
Spatial pooling is an important step in computer vision systems like Convolutional Neural Networks or the Bag-of-Words method. The spatial pooling purpose is to combine neighbouring descriptors to obtain a single descriptor ... -
Moderate deviation and restricted equivalence functions for measuring similarity between data
Altalhi, A. H.; Forcén Carvalho, Juan Ignacio; Pagola Barrio, Miguel ; Barrenechea Tartas, Edurne ; Bustince Sola, Humberto ; Takáč, Zdenko (Elsevier, 2019)
Artículo / Artikulua
In this work we study the relation between moderate deviation functions, restricted dissimilarity functions and restricted equivalence functions. We use moderate deviation functions in order to measure the similarity or ... -
Nuevos métodos para la combinación de características en procesamiento de imágenes
(2021) Tesis doctoral / Doktoretza tesia
En esta memoria estudiamos diferentes problemas abiertos entorno a la agregación de información y presentamos el estudio de nuevas técnicas de agregación de características de imágenes para mejorar el rendimiento en los ...
