Cell Microscopic Segmentation with Spiking Neuron Networks

Boudjelal Meftah (1, 2) , Olivier Lezoray (3) , Michel Lecluse (4) , Abdelkader Benyettou (5)

1 LRSBG - Equipe EDTEC
2 GREYC - Groupe de Recherche en Informatique, Image et Instrumentation de Caen
3 Equipe Image - Laboratoire GREYC - UMR6072
4 Site Louis Pasteur [CHPC]
5 SIMPA - Laboratoire Signal Image Parole

Spiking Neuron Networks (SNNs) overcome the computational power of neural networks made of thresholds or sigmoidal units. Indeed, SNNs add a new dimension, the temporal axis, to the representation capacity and the processing abilities of neural networks. In this paper, we present how SNN can be applied with efficacy for cell microscopic image segmentation. Results obtained confirm the validity of the approach. The strategy is performed on cytological color images. Quantitative measures are used to evaluate the resulting segmentations.

Mots clés: Cell microscopic images; Hebbian learning; Segmentation; Spiking Neuron Networks

Domaines: Traitement des images [eess.IV]

Boudjelal Meftah, Olivier Lezoray, Michel Lecluse, Abdelkader Benyettou. Cell Microscopic Segmentation with Spiking Neuron Networks. International Conference on Artificial Neural Networks, 2010, Thessaloniki, Greece. pp.117-126, ⟨10.1007/978-3-642-15819-3_16⟩. ⟨hal-00521071⟩