In this paper an optimized deep Convolutional Neural Network (CNN) for the automatic classification of Scanning Electron Microscope (SEM) images of homogeneous (HNF) and nonhomogeneous nanofibers (NHNF) produced by electrospinnig process is presented. Specifically, SEM images are used as input of a Deep Learning (DL) framework consisting of: a Sobel filter based pre-processing stage followed by a CNN classifier. Here, such DL architecture is denoted as SoCNNet. The Polyvinylacetate (PVAc) SEM image of NHNF and HNF dataset collected at the Materials for Environmental and Energy Sustainability Laboratory of the University Mediterranea of Reggio Calabria (Italy) is used to evaluate the performance of the developed system. Experimental results (average accuracy rate up-to 80.27% 0.0048) demonstrate the potential effectiveness of the proposed SoCNNet in the industrial chain of nanofibers production.

SoCNNet: An Optimized Sobel Filter Based Convolutional Neural Network for SEM Images Classification of Nanomaterials

Ieracitano C.
;
Mammone Nadia;Versaci M.;Morabito F. C.
2021

Abstract

In this paper an optimized deep Convolutional Neural Network (CNN) for the automatic classification of Scanning Electron Microscope (SEM) images of homogeneous (HNF) and nonhomogeneous nanofibers (NHNF) produced by electrospinnig process is presented. Specifically, SEM images are used as input of a Deep Learning (DL) framework consisting of: a Sobel filter based pre-processing stage followed by a CNN classifier. Here, such DL architecture is denoted as SoCNNet. The Polyvinylacetate (PVAc) SEM image of NHNF and HNF dataset collected at the Materials for Environmental and Energy Sustainability Laboratory of the University Mediterranea of Reggio Calabria (Italy) is used to evaluate the performance of the developed system. Experimental results (average accuracy rate up-to 80.27% 0.0048) demonstrate the potential effectiveness of the proposed SoCNNet in the industrial chain of nanofibers production.
978-981-15-5093-5
Laplacian and Sobel Filters
Convolutional Neural Networks
Fuzzy Logic
Nanofibers
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/20.500.12318/64088
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact