article · Scientific Reports
Artificial intelligence and deep learning provide powerful tools for examining complex visual data in materials science, notably scanning electron microscopy images of nanomaterials. Analysing these images manually can overlook subtle morphological patterns. To improve classification, a framework was developed to categorise nanostructures into nanowires, fibres, and tips. Because datasets often contain uneven category distributions, the Synthetic Minority Over-sampling Technique was applied at both pixel and deep feature levels to resolve class imbalance. Deep features were derived using a ResNet50 network, while transfer learning utilized SqueezeNet, ShuffleNet, and GoogLeNet architectures, alongside a multi-layer perceptron. Both balancing strategies proved effective. The pixel-level method attained a classification accuracy of 98.35% with GoogLeNet and ShuffleNet. Meanwhile, the feature-level approach reached 97.44% accuracy, presenting a computationally efficient alternative for automated characterisation.
Nanomaterials possess distinct structures that dictate their real-world performance, but categorising them through manual microscope inspection is difficult and prone to oversight. Automated image classification makes the identification of nanoscale features faster and more reliable. By resolving data imbalance issues, these techniques ensure that rare nanomaterial structures are accurately identified without demanding impractical computational resources.
The method could be integrated into software for scanning electron microscopes or materials analysis platforms, aiding materials scientists and quality assurance teams in characterising nanostructures. The abstract shows applied testing on image datasets, putting the technology at an applied research stage. Further software development would be necessary to package the models into commercially viable tools for automated laboratory or industrial inspection systems.
AI-generated from the published abstract. Always read the original work before citing.
Materials science investigates the relationships between a material's structure, properties, and fabrication processes. Recently, artificial intelligence (AI) and deep learning (DL) techniques have significantly enhanced the ability to analyze complex visual data, particularly in scanning electron microscopy (SEM) images. These approaches enable the detection of subtle morphological patterns that may not be easily identified through manual inspection, facilitating more accurate characterization of nanomaterials. In this study, a multi-class classification framework is proposed for SEM images of nanostructures, categorized into nanowires, fibers, and tips (NFT). To address the issue of class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was incorporated using two complementary strategies: pixel-level and feature-level representations. In the pixel-level approach, synthetic samples were generated directly from flattened image data, while in the feature-level approach, deep features were first extracted using a pre-trained ResNet50 model before applying SMOTE. For classification, transfer learning was employed using three convolutional neural network architectures: SqueezeNet, ShuffleNet, and GoogLeNet. In addition, a Multi-Layer Perceptron (MLP) classifier was used for feature-level representations. The experimental results demonstrate that both SMOTE strategies effectively address class imbalance, while the pixel-level approach achieved the highest classification performance. The pixel-level approach achieved a classification accuracy of up to 98.35% using GoogLeNet and ShuffleNet, whereas the feature-level approach achieved an accuracy of 97.44% while offering a computationally efficient alternative. These findings highlight the effectiveness of combining SMOTE with transfer learning for handling imbalanced SEM datasets and illustrate the trade-off between classification performance and computational efficiency.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1038/s41598-026-63864-7
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
