Publications (23)
Adapting the Hypersphere Loss Function from Anomaly Detection to Anomaly Segmentation
Joao P. C. Bertoldo, Santiago Velasco-Forero, Jesus Angulo +1
We propose an incremental improvement to Fully Convolutional Data Description (FCDD), an adaptation of the one-class classification approach from anomaly detection to image anomaly…
Some open questions on morphological operators and representations in the deep learning era
Jesus Angulo
During recent years, the renaissance of neural networks as the major machine learning paradigm and more specifically, the confirmation that deep learning techniques provide state-o…
Fast computation of all pairs of geodesic distances
Guillaume Noyel, Jesus Angulo, Dominique Jeulin
Computing an array of all pairs of geodesic distances between the pixels of an image is time consuming. In the sequel, we introduce new methods exploiting the redundancy of geodesi…
Morphological adjunctions represented by matrices in max-plus algebra for signal and image processing
Samy Blusseau, Santiago Velasco-Forero, Jesus Angulo +1
In discrete signal and image processing, many dilations and erosions can be written as the max-plus and min-plus product of a matrix on a vector. Previous studies considered operat…
Scale Equivariant Neural Networks with Morphological Scale-Spaces
Mateus Sangalli, Samy Blusseau, Santiago Velasco-Forero +1
The translation equivariance of convolutions can make convolutional neural networks translation equivariant or invariant. Equivariance to other transformations (e.g. rotations, aff…
Morphological segmentation of hyperspectral images
Guillaume Noyel, Jesus Angulo, Dominique Jeulin
The present paper develops a general methodology for the morphological segmentation of hyperspectral images, i.e., with an important number of channels. This approach, based on wat…