Logarithmic Morphological Neural Nets robust to lighting variations

TL;DR

This paper introduces a novel morphological neural network based on Logarithmic Mathematical Morphology that is inherently robust to lighting variations, improving image processing under different illumination conditions.

Contribution

It presents a new neural network framework using LMM and LIP models to achieve robustness to lighting changes, which was not addressed by previous morphological neural networks.

Findings

The network effectively maintains performance despite lighting variations.

It successfully learns structuring functions that are invariant to light intensity changes.

Experimental results confirm the robustness of the proposed approach.

Abstract

Morphological neural networks allow to learn the weights of a structuring function knowing the desired output image. However, those networks are not intrinsically robust to lighting variations in images with an optical cause, such as a change of light intensity. In this paper, we introduce a morphological neural network which possesses such a robustness to lighting variations. It is based on the recent framework of Logarithmic Mathematical Morphology (LMM), i.e. Mathematical Morphology defined with the Logarithmic Image Processing (LIP) model. This model has a LIP additive law which simulates in images a variation of the light intensity. We especially learn the structuring function of a LMM operator robust to those variations, namely : the map of LIP-additive Asplund distances. Results in images show that our neural network verifies the required property.