NFSDense201: microstructure image classification based on non-fixed size patch division with pre-trained DenseNet201 layers
Article
Barua, Prabal Datta, Dogan, Sengul, Kavuran, Gurkan, Tuncer, Turker, Tan, Ru-San and Acharya, U. Rajendra. 2023. "NFSDense201: microstructure image classification based on non-fixed size patch division with pre-trained DenseNet201 layers." Neural Computing and Applications. 35 (30), pp. 22253-22263. https://doi.org/10.1007/s00521-023-08825-1
| Article Title | NFSDense201: microstructure image classification based on non-fixed size patch division with pre-trained DenseNet201 layers |
|---|---|
| Article Category | Article |
| Authors | Barua, Prabal Datta, Dogan, Sengul, Kavuran, Gurkan, Tuncer, Turker, Tan, Ru-San and Acharya, U. Rajendra |
| Journal Title | Neural Computing and Applications |
| Journal Citation | 35 (30), pp. 22253-22263 |
| Number of Pages | 11 |
| Year | 2023 |
| Place of Publication | United Kingdom |
| Digital Object Identifier (DOI) | https://doi.org/10.1007/s00521-023-08825-1 |
| Web Address (URL) | https://link.springer.com/article/10.1007/s00521-023-08825-1 |
| Abstract | 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: “biological,” “fibers,” “film-coated surfaces,” “MEMS devices and electrodes,” “nanowires,” “particles,” “pattern surfaces,” “porous sponge,” “powder,” and “tips,” 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. |
| Keywords | Deep feature engineering; Non-fixed size patch division; SEM image classification ; DenseNet201 |
| ANZSRC Field of Research 2020 | 400306. Computational physiology |
| Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
| Byline Affiliations | School of Business |
| University of Technology Sydney | |
| Australian International Institute of Higher Education, Australia | |
| University of New England | |
| Taylor’s University, Malaysia | |
| SRM Institute of Science and Technology, India | |
| Kumamoto University, Japan | |
| University of Sydney | |
| Firat University, Turkey | |
| Malatya Turgut Ozal University, Turkiye | |
| National Heart Centre, Singapore | |
| Duke-NUS Medical School, Singapore | |
| School of Mathematics, Physics and Computing |
Permalink -
https://research.usq.edu.au/item/z1v63/nfsdense201-microstructure-image-classification-based-on-non-fixed-size-patch-division-with-pre-trained-densenet201-layers
63
total views0
total downloads7
views this month0
downloads this month