The paper proposes a novel approach for gray scale images segmentation . It is based on multiple features extraction from single feature per image pixel, using Echo state network . The newly extractedfeatures — reservoir equilibrium states — reveal hidden image characteristicsthat improve its segmentation via a clustering algorithm . The proposed approach is tested on the benchmark image Lena. Lena. It was demonstrated that the intrinsic plasticity tuning of reservoir fits itsequilibrium states to the original image intensity distribution .

Author(s) : Petia Koprinkova-Hristova

Links : PDF - Abstract

Code :
Coursera

Keywords : image - approach - segmentation - reservoir - states -

Leave a Reply

Your email address will not be published. Required fields are marked *