17
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Neural Network for Nanoscience Scanning Electron Microscope Image Recognition

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          In this paper we applied transfer learning techniques for image recognition, automatic categorization, and labeling of nanoscience images obtained by scanning electron microscope (SEM). Roughly 20,000 SEM images were manually classified into 10 categories to form a labeled training set, which can be used as a reference set for future applications of deep learning enhanced algorithms in the nanoscience domain. The categories chosen spanned the range of 0-Dimensional (0D) objects such as particles, 1D nanowires and fibres, 2D films and coated surfaces, and 3D patterned surfaces such as pillars. The training set was used to retrain on the SEM dataset and to compare many convolutional neural network models (Inception-v3, Inception-v4, ResNet). We obtained compatible results by performing a feature extraction of the different models on the same dataset. We performed additional analysis of the classifier on a second test set to further investigate the results both on particular cases and from a statistical point of view. Our algorithm was able to successfully classify around 90% of a test dataset consisting of SEM images, while reduced accuracy was found in the case of images at the boundary between two categories or containing elements of multiple categories. In these cases, the image classification did not identify a predominant category with a high score. We used the statistical outcomes from testing to deploy a semi-automatic workflow able to classify and label images generated by the SEM. Finally, a separate training was performed to determine the volume fraction of coherently aligned nanowires in SEM images. The results were compared with what was obtained using the Local Gradient Orientation method. This example demonstrates the versatility and the potential of transfer learning to address specific tasks of interest in nanoscience applications.

          Related collections

          Most cited references7

          • Record: found
          • Abstract: not found
          • Article: not found

          Nanowire photonics

            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Modulation of anisotropy in electrospun tissue-engineering scaffolds: Analysis of fiber alignment by the fast Fourier transform.

            We describe the use of the fast Fourier transform (FFT) in the measurement of anisotropy in electrospun scaffolds of gelatin as a function of the starting conditions. In electrospinning, fiber alignment and overall scaffold anisotropy can be manipulated by controlling the motion of the collecting mandrel with respect to the source electrospinning solution. By using FFT to assign relative alignment values to an electrospun matrix it is possible to systematically evaluate how different processing variables impact the structure and material properties of a scaffold. Gelatin was suspended at varying concentrations (80, 100, 130, 150 mg/ml) and electrospun from 2,2,2 trifluoroethanol onto rotating mandrels (200-7000 RPM). At each starting concentration, fiber diameter remained constant over a wide range of mandrel RPM. Scaffold anisotropy developed as a function of fiber diameter and mandrel RPM. The induction of varying degrees of anisotropy imparted distinctive material properties to the electrospun scaffolds. The FFT is a rapid method for evaluating fiber alignment in tissue-engineering materials.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              The art of aligning one-dimensional (1D) nanostructures.

              One-dimensional (1D) nanostructures, including polymeric, small molecule and inorganic types, are currently being investigated in great detail for their unique mechanical, optical, electronic properties and potential implementation as devices. To integrate 1D nanostructures into device applications, it is of importance to align such nanostructures in a parallel, scalable, and highly reproducible manner independent of the specific materials. Well aligned 1D nanostructures might exhibit superior properties that are not found in their disordered counterparts, allowing promising applications in diverse fields. This critical review summarizes the recent work in the alignment of polymeric, small molecule and inorganic 1D nanostructures, in particular, the advantages and drawbacks of various aligning approaches. Discussion is focused on an advanced strategy to precisely position each 1D nanostructure by superhydrophobic pillar-structured surfaces. The research prospects and directions of this rapidly developing field are also briefly addressed (123 references).
                Bookmark

                Author and article information

                Contributors
                aversa@iom.cnr.it
                Journal
                Sci Rep
                Sci Rep
                Scientific Reports
                Nature Publishing Group UK (London )
                2045-2322
                16 October 2017
                16 October 2017
                2017
                : 7
                : 13282
                Affiliations
                [1 ]ISNI 0000000121885934, GRID grid.5335.0, Institute for Manufacturing, Department of Engineering, University of Cambridge, ; 17 Charles Babbage Road, Cambridge, CB3 0FS United Kingdom
                [2 ]CNR-IOM Istituto di Officina dei Materiali c/o SISSA, via Bonomea 265, 34136 Trieste, Italy
                [3 ]eXact-Lab srl, via Beirut 2, 34151 Trieste, Italy
                [4 ]ISNI 0000 0004 1759 4706, GRID grid.419994.8, CNR-IOM, TASC Laboratory, Area Science Park, ; Basovizza S.S. 14 km 163.5, Trieste, 34149 Italy
                [5 ]Elegans.io Ltd, Bellside House 4th Floor, 4 Elthorne Road, London, N19 4AG United Kingdom
                Article
                13565
                10.1038/s41598-017-13565-z
                5643492
                29038550
                d28d5768-a487-4cf0-9a2e-5ad3155e9888
                © The Author(s) 2017

                Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.

                History
                : 24 May 2017
                : 26 September 2017
                Categories
                Article
                Custom metadata
                © The Author(s) 2017

                Uncategorized
                Uncategorized

                Comments

                Comment on this article