no code implementations • 20 Apr 2022 • Guillaume Noyel, Emile Barbier--Renard, Michel Jourlin, Thierry Fournel
In this paper, we introduce a morphological neural network which possesses such a robustness to lighting variations.
no code implementations • 4 Sep 2019 • Guillaume Noyel, Michel Jourlin
Importantly, they are efficient to detect patterns in low-contrast images with a template acquired under a different lighting.
no code implementations • 17 Apr 2019 • Guillaume Noyel, Michel Jourlin
The second, the LIP-multiplicative homogeneity criterion, is based on the LIP-multiplicative law and is insensitive to changes due to variations of the object thickness or opacity.
no code implementations • 27 Jun 2018 • Michel Jourlin, Guillaume Noyel
The current paper deals with the role played by Logarithmic Image Processing (LIP) operators for evaluating the homogeneity of a region.
no code implementations • 2 Mar 2018 • Guillaume Noyel, Michel Jourlin
Our contribution consists in extending the Aspl{\"u}nd's metric to colour and multivariate images using the LIP framework.
no code implementations • 23 Aug 2017 • Guillaume Noyel, Michel Jourlin
We introduce a simple expression for the map of Asplund's distances with the multiplicative Logarithmic Image Processing (LIP) law.
no code implementations • 27 Jan 2017 • Guillaume Noyel, Michel Jourlin
Using a flat structuring element, the expression of the map of Asplund's distances can be simplified with a dilation and an erosion of the image; these mappings stays in the lattice of the images.
no code implementations • 31 Aug 2016 • Guillaume Noyel, Michel Jourlin
Aspl\"und 's metric, which is useful for pattern matching, consists in a double-sided probing, i. e. the over-graph and the sub-graph of a function are probed jointly.