{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:43:40Z","timestamp":1772120620599,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"30","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001795","name":"University of Southern Queensland","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001795","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2023,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In the field of nanoscience, the scanning electron microscope (SEM) is widely employed to visualize the surface topography and composition of materials. In this study, we present a novel SEM image classification model called NFSDense201, which incorporates several key components. Firstly, we propose a unique nested patch division approach that divides each input image into four patches of varying dimensions. Secondly, we utilize DenseNet201, a deep neural network pretrained on ImageNet1k, to extract 2920 deep features from the last fully connected and global average pooling layers. Thirdly, we introduce an iterative neighborhood component analysis function to select the most discriminative features from the merged feature vector, which is formed by concatenating the four feature vectors extracted per input image. This process results in a final feature vector of optimal length 698. Lastly, we employ a standard shallow support vector machine classifier to perform the actual classification. To evaluate the performance of NFSDense201, we conducted experiments using a large public SEM image dataset. The dataset consists of 972, 162, 326, 4590, 3820, 3925, 4755, 181, 917, and 1624.jpeg images belonging to the following microstructural categories: \u201cbiological,\u201d \u201cfibers,\u201d \u201cfilm-coated surfaces,\u201d \u201cMEMS devices and electrodes,\u201d \u201cnanowires,\u201d \u201cparticles,\u201d \u201cpattern surfaces,\u201d \u201cporous sponge,\u201d \u201cpowder,\u201d and \u201ctips,\u201d respectively. For both four-class and ten-class classification tasks, we evaluated NFSDense201 using subsets of the dataset containing 5080 and 21,272 images, respectively. The results demonstrate the superior performance of NFSDense201, achieving a four-class classification accuracy rate of 99.53% and a ten-class classification accuracy rate of 97.09%. These accuracy rates compare favorably against previously published SEM image classification models. Additionally, we report the performance of NFSDense201 for each class in the dataset.<\/jats:p>","DOI":"10.1007\/s00521-023-08825-1","type":"journal-article","created":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T09:02:16Z","timestamp":1691398936000},"page":"22253-22263","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["NFSDense201: microstructure image classification based on non-fixed size patch division with pre-trained DenseNet201 layers"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5117-8333","authenticated-orcid":false,"given":"Prabal Datta","family":"Barua","sequence":"first","affiliation":[]},{"given":"Sengul","family":"Dogan","sequence":"additional","affiliation":[]},{"given":"Gurkan","family":"Kavuran","sequence":"additional","affiliation":[]},{"given":"Turker","family":"Tuncer","sequence":"additional","affiliation":[]},{"given":"Ru-San","family":"Tan","sequence":"additional","affiliation":[]},{"given":"U.","family":"Rajendra Acharya","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,7]]},"reference":[{"key":"8825_CR1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.sab.2013.04.008","volume":"86","author":"FC Adams","year":"2013","unstructured":"Adams FC, Barbante C (2013) Nanoscience, nanotechnology and spectrometry. Spectrochim Acta Part B 86:3\u201313","journal-title":"Spectrochim Acta Part B"},{"key":"8825_CR2","first-page":"1","volume-title":"Interface science and technology","author":"M Nasrollahzadeh","year":"2019","unstructured":"Nasrollahzadeh M, Sajadi SM, Sajjadi M, Issaabadi Z (2019) An introduction to nanotechnology. Interface science and technology, vol 28. Elsevier, Amsterdam, pp 1\u201327"},{"issue":"7","key":"8825_CR3","doi-asserted-by":"publisher","first-page":"1056","DOI":"10.1016\/j.pmatsci.2013.04.001","volume":"58","author":"MJ Hanus","year":"2013","unstructured":"Hanus MJ, Harris AT (2013) Nanotechnology innovations for the construction industry. Prog Mater Sci 58(7):1056\u20131102","journal-title":"Prog Mater Sci"},{"key":"8825_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-98482-7","volume-title":"A beginners' guide to scanning electron microscopy,","author":"A Ul-Hamid","year":"2018","unstructured":"Ul-Hamid A (2018) A beginners\u2019 guide to scanning electron microscopy, vol 1. Springer, Berlin"},{"key":"8825_CR5","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/6871785","author":"J Rydz","year":"2019","unstructured":"Rydz J, \u0160i\u0161kov\u00e1 A, Andicsov\u00e1 Eckstein A (2019) Scanning electron microscopy and atomic force microscopy: Topographic and dynamical surface studies of blends, composites, and hybrid functional materials for sustainable future. Adv Mater Sci Eng. https:\/\/doi.org\/10.1155\/2019\/6871785","journal-title":"Adv Mater Sci Eng"},{"issue":"1","key":"8825_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.172","volume":"5","author":"R Aversa","year":"2018","unstructured":"Aversa R, Modarres MH, Cozzini S, Ciancio R, Chiusole A (2018) The first annotated set of scanning electron microscopy images for nanoscience. Sci Data 5(1):1\u201310","journal-title":"Sci Data"},{"key":"8825_CR7","unstructured":"NFFA-EUROPE (2016) Draft metadata standard for nanoscience data. NFFA project deliverable D11.2, http:\/\/www.nffa.eu\/media\/124786\/d112-draft-metadata-standard-for-nanoscience-data_20160225-v1.pdf"},{"issue":"1","key":"8825_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.18","volume":"3","author":"MD Wilkinson","year":"2016","unstructured":"Wilkinson MD, Dumontier M, Aalbersberg IJ, Appleton G, Axton M, Baak A, Blomberg N, Boiten J-W, da Silva Santos LB, Bourne PE (2016) The FAIR guiding principles for scientific data management and stewardship. Sci Data 3(1):1\u20139","journal-title":"Sci Data"},{"issue":"1","key":"8825_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-017-13565-z","volume":"7","author":"MH Modarres","year":"2017","unstructured":"Modarres MH, Aversa R, Cozzini S, Ciancio R, Leto A, Brandino GP (2017) Neural network for nanoscience scanning electron microscope image recognition. Sci Rep 7(1):1\u201312","journal-title":"Sci Rep"},{"key":"8825_CR10","doi-asserted-by":"publisher","first-page":"108178","DOI":"10.1016\/j.petrol.2020.108178","volume":"200","author":"C Li","year":"2021","unstructured":"Li C, Wang D, Kong L (2021) Application of machine learning techniques in mineral classification for scanning electron microscopy-energy dispersive X-ray spectroscopy (SEM-EDS) images. J Petrol Sci Eng 200:108178","journal-title":"J Petrol Sci Eng"},{"key":"8825_CR11","doi-asserted-by":"publisher","first-page":"113125","DOI":"10.1016\/j.ultramic.2020.113125","volume":"219","author":"AY Kharin","year":"2020","unstructured":"Kharin AY (2020) Deep learning for scanning electron microscopy: Synthetic data for the nanoparticles detection. Ultramicroscopy 219:113125","journal-title":"Ultramicroscopy"},{"key":"8825_CR12","doi-asserted-by":"publisher","first-page":"100087","DOI":"10.1016\/j.mtnano.2020.100087","volume":"11","author":"M Ge","year":"2020","unstructured":"Ge M, Su F, Zhao Z, Su D (2020) Deep learning analysis on microscopic imaging in materials science. Materials Today Nano 11:100087","journal-title":"Materials Today Nano"},{"issue":"6","key":"8825_CR13","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390","journal-title":"Commun ACM"},{"key":"8825_CR14","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"8825_CR15","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1016\/j.commatsci.2015.08.011","volume":"110","author":"BL DeCost","year":"2015","unstructured":"DeCost BL, Holm EA (2015) A computer vision approach for automated analysis and classification of microstructural image data. Comput Mater Sci 110:126\u2013133","journal-title":"Comput Mater Sci"},{"issue":"4","key":"8825_CR16","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1080\/10589750802258986","volume":"23","author":"VHC de Albuquerque","year":"2008","unstructured":"de Albuquerque VHC, Cortez PC, de Alexandria AR, Tavares JMR (2008) A new solution for automatic microstructures analysis from images based on a backpropagation artificial neural network. Nondestruct Test Eval 23(4):273\u2013283","journal-title":"Nondestruct Test Eval"},{"key":"8825_CR17","doi-asserted-by":"publisher","first-page":"233030","DOI":"10.1016\/j.jpowsour.2023.233030","volume":"570","author":"M Osenberg","year":"2023","unstructured":"Osenberg M, Hilger A, Neumann M, Wagner A, Bohn N, Binder JR, Schmidt V, Banhart J, Manke I (2023) Classification of FIB\/SEM-tomography images for highly porous multiphase materials using random forest classifiers. J Power Sources 570:233030","journal-title":"J Power Sources"},{"key":"8825_CR18","doi-asserted-by":"publisher","first-page":"112250","DOI":"10.1016\/j.commatsci.2023.112250","volume":"226","author":"Y Han","year":"2023","unstructured":"Han Y, Liu Y, Chen Q (2023) Data augmentation in material images using the improved HP-VAE-GAN. Comput Mater Sci 226:112250. https:\/\/doi.org\/10.1016\/j.commatsci.2023.112250","journal-title":"Comput Mater Sci"},{"key":"8825_CR19","doi-asserted-by":"publisher","first-page":"112135","DOI":"10.1016\/j.commatsci.2023.112135","volume":"223","author":"G Dahy","year":"2023","unstructured":"Dahy G, Soliman MM, Alshater H, Slowik A, Hassanien AE (2023) Optimized deep networks for the classification of nanoparticles in scanning electron microscopy imaging. Comput Mater Sci 223:112135","journal-title":"Comput Mater Sci"},{"key":"8825_CR20","doi-asserted-by":"publisher","first-page":"160303","DOI":"10.1016\/j.scitotenv.2022.160303","volume":"859","author":"JJ Scott-Fordsmand","year":"2023","unstructured":"Scott-Fordsmand JJ, Amorim MJ (2023) Using Machine Learning to make nanomaterials sustainable. Sci Total Environ 859:160303","journal-title":"Sci Total Environ"},{"key":"8825_CR21","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"8825_CR22","unstructured":"Tolstikhin I, Houlsby N, Kolesnikov A, Beyer L, Zhai X, Unterthiner T, Yung J, Keysers D, Uszkoreit J, Lucic M (2021) MLP-Mixer: An all-MLP Architecture for Vision. arXiv preprint https:\/\/arxiv.org\/abs\/2105.01601"},{"key":"8825_CR23","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L (2017) Weinberger KQ Densely connected convolutional networks. In: proceedings of the IEEE conference on computer vision and pattern recognition. pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"8825_CR24","doi-asserted-by":"publisher","first-page":"84532","DOI":"10.1109\/ACCESS.2020.2992641","volume":"8","author":"T Tuncer","year":"2020","unstructured":"Tuncer T, Dogan S, \u00d6zyurt F, Belhaouari SB, Bensmail H (2020) Novel multi center and threshold ternary pattern based method for disease detection method using voice. IEEE Access 8:84532\u201384540","journal-title":"IEEE Access"},{"key":"8825_CR25","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-1-4615-5703-6_3","volume-title":"Nonlinear Modeling","author":"V Vapnik","year":"1998","unstructured":"Vapnik V (1998) The support vector method of function estimation. Nonlinear Modeling. Springer, Berlin, pp 55\u201385"},{"key":"8825_CR26","volume-title":"The nature of statistical learning theory","author":"V Vapnik","year":"2013","unstructured":"Vapnik V (2013) The nature of statistical learning theory. Springer, Berlin"},{"key":"8825_CR27","unstructured":"Powers DM (2020) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint https:\/\/arxiv.org\/abs\/2010.16061"},{"issue":"2","key":"8825_CR28","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s00357-008-9023-7","volume":"25","author":"MJ Warrens","year":"2008","unstructured":"Warrens MJ (2008) On the equivalence of Cohen\u2019s kappa and the hubert-arabie adjusted rand index. J Classif 25(2):177\u2013183","journal-title":"J Classif"},{"key":"8825_CR29","doi-asserted-by":"publisher","first-page":"102198","DOI":"10.1016\/j.mtcomm.2021.102198","volume":"27","author":"G Kavuran","year":"2021","unstructured":"Kavuran G (2021) SEM-Net: deep features selections with binary particle swarm optimization Method for classification of scanning electron microscope images. Mater Today Commun 27:102198","journal-title":"Mater Today Commun"},{"key":"8825_CR30","doi-asserted-by":"publisher","first-page":"104092","DOI":"10.1016\/j.engappai.2020.104092","volume":"97","author":"J Zhang","year":"2021","unstructured":"Zhang J, Liu M, Xiong P, Du H, Zhang H, Lin F, Hou Z, Liu X (2021) A multi-dimensional association information analysis approach to automated detection and localization of myocardial infarction. Eng Appl Artif Intell 97:104092","journal-title":"Eng Appl Artif Intell"},{"issue":"1","key":"8825_CR31","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1109\/JAS.2020.1003387","volume":"8","author":"C Ieracitano","year":"2020","unstructured":"Ieracitano C, Paviglianiti A, Campolo M, Hussain A, Pasero E, Morabito FC (2020) A novel automatic classification system based on hybrid unsupervised and supervised machine learning for electrospun nanofibers. IEEE\/CAA J Autom Sinica 8(1):64\u201376","journal-title":"IEEE\/CAA J Autom Sinica"},{"key":"8825_CR32","doi-asserted-by":"publisher","first-page":"101514","DOI":"10.1016\/j.mtcomm.2020.101514","volume":"25","author":"K Tsutsui","year":"2020","unstructured":"Tsutsui K, Terasaki H, Uto K, Maemura T, Hiramatsu S, Hayashi K, Moriguchi K, Morito S (2020) A methodology of steel microstructure recognition using SEM images by machine learning based on textural analysis. Mater Today Commun 25:101514","journal-title":"Mater Today Commun"},{"key":"8825_CR33","doi-asserted-by":"crossref","unstructured":"Tian X, Daigle H, Jiang H (2018) Feature detection for digital images using machine learning algorithms and image processing. In: SPE\/AAPG\/SEG Unconventional Resources Technology Conference, OnePetro","DOI":"10.15530\/urtec-2018-2886325"},{"key":"8825_CR34","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/9673724","author":"C Yin","year":"2020","unstructured":"Yin C, Cheng X, Liu X, Zhao M (2020) Identification and classification of atmospheric particles based on SEM images using convolutional neural network with attention mechanism. Complexity. https:\/\/doi.org\/10.1155\/2020\/9673724","journal-title":"Complexity"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08825-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08825-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08825-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T15:03:37Z","timestamp":1694876617000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08825-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":34,"journal-issue":{"issue":"30","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["8825"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08825-1","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"21 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors of this manuscript declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}