{
  "abstract": "We evaluate ten convolutional neural networks (CNNs) and ten transformer/attention architectures for nine-category surface classification using 41,756 balanced StructDamage images. A frozen ImageNet-pretrained ResNet18 encoder and learned head use 33,352 training, 4202 validation and 4202 test images grouped by inferred augmentation family. Test accuracy is 98.88%, macro-F1 is 0.9881, and the 95% component-bootstrap accuracy interval is 98.42-99.26%. Content screening retains 4102 test images and 98.85% accuracy. Nevertheless, cross-partition exact matches and candidate source-prefix overlap prevent treating these results as independent-site validation. The separate random-initialization screen uses 1800 training images, 900 validation images, the common test set, 64 × 64 inputs and five epochs. DenseNet121 leads with 88.34% accuracy; XCiT-Tiny leads the transformer/attention group with 84.75% accuracy. Eighteen models select the final epoch, so the comparison does not establish convergence-equivalent superiority. With 5400 training images, all twenty accuracies increase and the between-budget rank correlation is 0.850. Component-aware comparisons and wall/deck error analysis qualify the ranking. The findings concern surface-category recognition, not defect localization, damage severity or structural safety.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Electrical and Electronic Engineering Technology, University of Johannesburg, Johannesburg 2092, South Africa.",
    "Discipline of Civil Engineering, University of KwaZulu Natal, Durban 4041, South Africa.",
    "National Home Builders Registration Council, Durban 4001, South Africa."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Bonginkosi A Thango",
      "orcid": "0000-0003-3635-0988"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Sipho G Thango"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/61qbfp420bhjf.bib",
  "cited_by": 0,
  "doi": "10.3390/jimaging12100487",
  "fulltext_url": "https://europepmc.org/articles/PMC13705699",
  "id": "61qbfp420bhjf",
  "issns": [
    "2313-433X"
  ],
  "landing_url": "https://europepmc.org/article/MED/42930638",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2205|Infrastructure Maintenance and Monitoring"
    ]
  ],
  "openalex": "W7220731952",
  "pdf_url": "https://europepmc.org/articles/PMC13705699?pdf=render",
  "pmcid": "PMC13705699",
  "pmid": "42930638",
  "published": "2026-10-06",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/61qbfp420bhjf.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:22:01Z",
      "native_id": "MED:42930638",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42930638"
    }
  ],
  "subjects": [],
  "title": "Assessment of Convolutional Neural Network and Vision Transformer Architectures for Structural Surface Classification.",
  "title_text": "Assessment of Convolutional Neural Network and Vision Transformer Architectures for Structural Surface Classification.",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:22:01Z",
  "url": "https://research.draconitic.com/paper/61qbfp420bhjf",
  "venue": "Journal of imaging",
  "versions": []
}