Binary morphological neural network

Théodore Aouad (1) , Hugues Talbot (1)

1 OPIS - OPtimisation Imagerie et Santé

In the last ten years, Convolutional Neural Networks (CNNs) have formed the basis of deep-learning architectures for most computer vision tasks. However, they are not necessarily optimal. For example, mathematical morphology is known to be better suited to deal with binary images. In this work, we create a morphological neural network that handles binary inputs and outputs. We propose their construction inspired by CNNs to formulate layers adapted to such images by replacing convolutions with erosions and dilations. We give explainable theoretical results on whether or not the resulting learned networks are indeed morphological operators. We present promising experimental results designed to learn basic binary operators, and we have made our code publicly available online.

Mots clés: Mathematical morphology; binary; deep learning; machine learning; image processing

Domaines: Traitement des images [eess.IV]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Réseau de neurones [cs.NE]

Théodore Aouad, Hugues Talbot. Binary morphological neural network. IEEE International Conference on Image Processing (ICIP), Oct 2022, Bordeaux, France. pp.3276-3280. ⟨hal-03617249⟩