Search Results for author: Michel Jourlin

Found 8 papers, 0 papers with code

Logarithmic Morphological Neural Nets robust to lighting variations

no code implementations20 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.

Functional Asplund metrics for pattern matching, robust to variable lighting conditions

no code implementations4 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.

Region homogeneity in the Logarithmic Image Processing framework: application to region growing algorithms

no code implementations17 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.

Image Segmentation Semantic Segmentation

Homogeneity of a region in the logarithmic image processing framework: application to region growing algorithms

no code implementations27 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.

Aspl{ü}nd's metric defined in the Logarithmic Image Processing (LIP) framework for colour and multivariate images

no code implementations2 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.

A simple expression for the map of Asplund's distances with the multiplicative Logarithmic Image Processing (LIP) law

no code implementations23 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.

Double-sided probing by map of Asplund's distances using Logarithmic Image Processing in the framework of Mathematical Morphology

no code implementations27 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.

Spatio-Colour Asplünd 's Metric and Logarithmic Image Processing for Colour Images (LIPC)

no code implementations31 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.