CoChat

Performance Comparison of Multiple Convolutional Neural Networks for Concrete Defects Classification

Open access

The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.

Abstract

Periodical vision-based inspection is a principal form of structural health monitoring (SHM) technique. Over the last decades, vision-based artificial intelligence (AI) has successfully facilitated an effortless inspection system owing to its exceptional ability of accuracy of defects’ pattern recognition. However, most deep learning (DL)-based methods detect one specific type of defect, whereas DL has a high proficiency in multiple object detection. This study developed a dataset of two types of defects, i.e., concrete crack and spalling, and applied various pre-built convolutional neural network (CNN) models, i.e., VGG-19, ResNet-50, InceptionV3, Xception, and MobileNetV2 to classify these concrete defects. The dataset developed for this study has one of the largest collections of original images of concrete crack and spalling and avoided the augmentation process to replicate a more real-world condition, which makes the dataset one of a kind. Moreover, a detailed sensitivity analysis of hyper-parameters (i.e., optimizers, learning rate) was conducted to compare the classification models’ performance and identify the optimal image classification condition for the best-performed CNN model. After analyzing all the models, InceptionV3 outperformed all the other models with an accuracy of 91%, precision of 83%, and recall of 100%. The InceptionV3 model performed best with optimizer stochastic gradient descent (SGD) and a learning rate of 0.001.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/s22228714

Cites

43 of 43 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Workflow chart for defects classification.
Figure 1 Workflow chart for defects classification.CC BY · PubMed Central
Figure 2 Size of dataset. (a) Crack dataset. (b) Spalling dataset.
Figure 2 Size of dataset. (a) Crack dataset. (b) Spalling dataset.CC BY · PubMed Central
Figure 3 Sample images for defects dataset (a–c) crack and (d–f) spalling (image courtesy: TBT Engineering).
Figure 3 Sample images for defects dataset (a–c) crack and (d–f) spalling (image courtesy: TBT Engineering).CC BY · PubMed Central
Figure 4 Activation function (ReLu).
Figure 4 Activation function (ReLu).CC BY · PubMed Central
Figure 5 Defects classification: comparison of the evaluation metrics based on SGD and RMSprop optimization function for learning rate 0.001.
Figure 5 Defects classification: comparison of the evaluation metrics based on SGD and RMSprop optimization function for learning rate 0.001.CC BY · PubMed Central
Figure 6 Confusion matrix for InceptionV3 and Xception for optimizer SGD and learning rate 0.001. (a) InceptionV3 (SGD). (b) Xception (SGD).
Figure 6 Confusion matrix for InceptionV3 and Xception for optimizer SGD and learning rate 0.001. (a) InceptionV3 (SGD). (b) Xception (SGD).CC BY · PubMed Central
Figure 7 Defects classification with InceptionV3: result of the evaluation metrics and model loss for optimizer SGD and learning rate 0.0001.
Figure 7 Defects classification with InceptionV3: result of the evaluation metrics and model loss for optimizer SGD and learning rate 0.0001.CC BY · PubMed Central
Figure 8 Defects classification with InceptionV3: result of the evaluation metrics and model loss for optimizer SGD and learning rate 0.001.
Figure 8 Defects classification with InceptionV3: result of the evaluation metrics and model loss for optimizer SGD and learning rate 0.001.CC BY · PubMed Central
Figure 9 Defects classification with InceptionV3: result of the evaluation metrics and model loss for optimizer SGD and learning rate 0.01.
Figure 9 Defects classification with InceptionV3: result of the evaluation metrics and model loss for optimizer SGD and learning rate 0.01.CC BY · PubMed Central
Figure 10 Sample images for crack prediction using CNN models.
Figure 10 Sample images for crack prediction using CNN models.CC BY · PubMed Central
Figure 11 Sample images for spalling prediction using CNN.
Figure 11 Sample images for spalling prediction using CNN.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 2

  1. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
  2. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press.

Cited by

See all 34

Metadata

Authors
Arafin, P., Issa, A., & Billah, A. H. M. M.
Affiliations
  • Lakehead University (CA)
  • United Arab Emirates University (AE)
  • University of Calgary (CA)
Corresponding author
  • Issa, Anas
  • Billah, A. H. M. Muntasir
Venue
Sensors
Publisher
MDPI AG
Published
2022-11-11
Volume
22
Issue
22
Pages
8714
ISSN
1424-8220 (ISSN-L)
OpenAlex
W4309012905
Cited by
34
References
43
Citations by year
2026: 9 · 2025: 10 · 2024: 8 · 2023: 6 · 2022: 1
FWCI
2.81
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
NSERC (National Sciences and Engineering Research Council of Canada) (ALLRP 555258-20)
Topics
  • Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
  • Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
  • Physical Sciences › Engineering › Civil and Structural Engineering › Structural Health Monitoring Techniques
Keywords
concrete cracking, concrete spalling, structural health monitoring, image-based inspection, convolutional neural networks, InceptionV3, VGG19, ResNet50, MobileNetV2, Xception, hyperparameter sensitivity analysis, learning rate, optimizer comparison
MeSH terms
Artificial Intelligence, Neural Networks, Computer

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.