Skip to main content
SpringerLink
Log in

Automated hyperparameter tuning for crack image classification with deep learning

  • Neural Networks
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Deep learning methods have relevant applications in crack detection in buildings. However, one of the challenges in this field is the hyperparameter tuning process for convolutional neural networks (CNN). Thus, the objective of this paper is to propose a automated hyperparameter tuning approach for crack image classification. For this, a public dataset with 40,000 images of walls and floors of several buildings was used. The images are divided into two classes: negative (non-crack) and positive (crack). In this aspect, statistical methods are used for hyperparameter tuning, such as analysis of variance, Scott–Knott method and HyperTuningSK algorithm. Moreover, three new automated machine learning algorithms are proposed: AutoHyperTuningSK, AutoHyperTuningSK-test and AutoHyperTu-ningSK-DA. CNN architecture from the literature (MobileNet) and three types of hyperparameters (learning rate, optimizer and data augmentation) are analyzed. In general, the recommended configurations reached the best results in relation to unselected hyperparameters. In this regard, a selected combinations achieved a mean accuracy of around \(99\%\) (test experiments) in binary crack classification.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Algorithm 1
Algorithm 2
Algorithm 3
Algorithm 4
Algorithm 5
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Availability of data

The dataset analysed during the current study is available in the Mendeley repository, https://data.mendeley.com/datasets/5y9wdsg2zt/2.

Notes

  1. https://data.mendeley.com/datasets/5y9wdsg2zt/2.

  2. https://www.automl.org/deep-learning-2-0-extending-the-power-of-deep-learning-to-the-meta-level/.

  3. https://keras.io/api/keras_tuner/

References

  • Ali L, Alnajjar F, Khan W, Serhani MA, Al Jassmi H (2022) Bibliometric analysis and review of deep learning-based crack detection literature published between 2010 and 2022. Buildings 12(4):432

    Google Scholar 

  • Ali R, Chuah JH, Talip MSA, Mokhtar N, Shoaib MA (2022) Structural crack detection using deep convolutional neural networks. Autom Constr 133:103989

    Google Scholar 

  • Alipour M, Harris DK, Miller GR (2019) Robust pixel-level crack detection using deep fully convolutional neural networks. J Comput Civ Eng 33(6):04019040

    Google Scholar 

  • Atteia G, Abdel Samee N, El-Kenawy E-SM, Ibrahim A (2022) Cnn-hyperparameter optimization for diabetic maculopathy diagnosis in optical coherence tomography and fundus retinography. Mathematics 10(18):3274

    Google Scholar 

  • Balestriero R, Bottou L, LeCun Y (2022) The effects of regularization and data augmentation are class dependent. arXiv:2204.03632

  • Bang S, Park S, Kim H, Kim H (2019) Encoder-decoder network for pixel-level road crack detection in black-box images. Comput Aided Civ Infrastruct Eng 34(8):713–727

    Google Scholar 

  • Bartlett MS (1937) Properties of sufficiency and statistical tests. Proc R Soc Lond Ser A Math Phys Sci 160(901):268–282

    MATH  Google Scholar 

  • Basgalupp MP, Barros RC, de Sá AGC, Pappa GL, Mantovani RG, de Carvalho A, Freitas AA (2021) An extensive experimental evaluation of automated machine learning methods for recommending classification algorithms. Evol Intell 14(4):1895–1914

    Google Scholar 

  • Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13(2)

  • Bonidia RP, Santos APA, de Almeida BL, Stadler PF, da Rocha UN, Sanches DS, de Carvalho A C (2022) Bioautoml: automated feature engineering and metalearning to predict noncoding rnas in bacteria. Brief Bioinform 23(4):bbac218

  • Chen J, Zhang D, Suzauddola M, Nanehkaran YA, Sun Y (2021) Identification of plant disease images via a squeeze-and-excitation mobilenet model and twice transfer learning. IET Image Proc 15(5):1115–1127

    Google Scholar 

  • Chollet F, Allaire JJ (2018) Deep learning with R. Manning Publications, New York

    Google Scholar 

  • Dais D, Bal IE, Smyrou E, Sarhosis V (2021) Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning. Autom Constr 125:103606

    Google Scholar 

  • Dorafshan S, Thomas RJ, Maguire M (2018) Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete. Constr Build Mater 186:1031–1045

    Google Scholar 

  • Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12(7):2121–2159

    MathSciNet  MATH  Google Scholar 

  • Dung CV, Anh LD (2019) Autonomous concrete crack detection using deep fully convolutional neural network. Autom Constr 99:52–58

    Google Scholar 

  • Elfatimi E, Eryigit R, Elfatimi L (2022) Beans leaf diseases classification using mobilenet models. IEEE Access 10:9471–9482

    Google Scholar 

  • Elgendy M (2020) Deep learning for vision systems. Manning Publications, New York

    Google Scholar 

  • Feng X, Xiao L, Li W, Pei L, Sun Z, Ma Z, Shen H, Ju H (2020) Pavement crack detection and segmentation method based on improved deep learning fusion model. Math Probl Eng 2020:1–20

    Google Scholar 

  • Goay CH, Ahmad NS, Goh P (2021) Transient simulations of high-speed channels using cnn-lstm with an adaptive successive halving algorithm for automated hyperparameter optimizations. IEEE Access 9:127644–127663

    Google Scholar 

  • Gopalakrishnan K, Khaitan SK, Choudhary A, Agrawal A (2017) Deep convolutional neural networks with transfer learning for computer vision-based data-driven pavement distress detection. Constr Build Mater 157:322–330

    Google Scholar 

  • Guo J, Wang Q, Li Y (2021) Semi-supervised learning based on convolutional neural network and uncertainty filter for façade defects classification. Comput Aided Civ Infrastruct Eng 36(3):302–317

    Google Scholar 

  • Han T, Gois FNB, Oliveira R, Prates LR, Porto MMA (2021) Modeling the progression of covid-19 deaths using kalman filter and automl. Soft Comput 1–16

  • He X, Zhao K, Chu X (2021) Automl: a survey of the state-of-the-art. Knowl-Based Syst 212:106622

    Google Scholar 

  • Hirahara D, Takaya E, Takahara T, Ueda T (2020) Effects of data count and image scaling on deep learning training. PeerJ Comput Sci 6:e312

    Google Scholar 

  • Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861

  • Hu Y-Q, Yu Y (2020) A technical view on neural architecture search. Int J Mach Learn Cybern 11(4):795–811

    MathSciNet  Google Scholar 

  • Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 2261–2269

  • Hutter F, Kotthoff L, Vanschoren J (eds) (2019) Automated machine learning: methods, systems, challenges. Springer. http://automl.org/book

  • Imran J, Raman B (2020) Deep motion templates and extreme learning machine for sign language recognition. Vis Comput 36(6):1233–1246

    Google Scholar 

  • Jelihovschi EG, Faria JC, Allaman IB (2014) Scottknott: a package for performing the Scott–Knott clustering algorithm in r. TEMA-SBMAC 15(1):3–17

    MathSciNet  Google Scholar 

  • Kaddah W, Elbouz M, Ouerhani Y, Baltazart V, Desthieux M, Alfalou A (2019) Optimized minimal path selection (omps) method for automatic and unsupervised crack segmentation within two-dimensional pavement images. Vis Comput 35(9):1293–1309

    Google Scholar 

  • Kaddah W, Elbouz M, Ouerhani Y, Alfalou A, Desthieux M (2020) Automatic darkest filament detection (adfd): a new algorithm for crack extraction on two-dimensional pavement images. Vis Comput 36(7):1369–1384

    Google Scholar 

  • Kim B, Yuvaraj N, Sri Preethaa K, Arun Pandian R (2021) Surface crack detection using deep learning with shallow cnn architecture for enhanced computation. Neural Comput Appl 33(15):9289–9305

    Google Scholar 

  • Kouzehgar M, Tamilselvam YK, Heredia MV, Elara MR (2019) Self-reconfigurable façade-cleaning robot equipped with deep-learning-based crack detection based on convolutional neural networks. Autom Constr 108:102959

    Google Scholar 

  • Lahmar C, Idri A (2021) On the value of deep learning for diagnosing diabetic retinopathy. Health Technol 1–17

  • Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444

    Google Scholar 

  • Li L, Jamieson K, DeSalvo G, Rostamizadeh A, Talwalkar A (2017) Hyperband: a novel bandit-based approach to hyperparameter optimization. J Mach Learn Res 18(1):6765–6816

    MathSciNet  MATH  Google Scholar 

  • Li S, Zhao X (2019) Image-based concrete crack detection using convolutional neural network and exhaustive search technique. Adv Civ Eng 2019

  • Li K, Jin Y, Akram MW, Han R, Chen J (2020) Facial expression recognition with convolutional neural networks via a new face cropping and rotation strategy. Vis Comput 36(2):391–404

    Google Scholar 

  • Liu Z, Cao Y, Wang Y, Wang W (2019) Computer vision-based concrete crack detection using u-net fully convolutional networks. Autom Constr 104:129–139

    Google Scholar 

  • Maeda H, Sekimoto Y, Seto T, Kashiyama T, Omata H (2018) Road damage detection and classification using deep neural networks with smartphone images. Comput Aided Civ Infrastruct Eng 33(12):1127–1141

    Google Scholar 

  • Mantovani RG, Rossi AL, Alcobaça E, Vanschoren J, de Carvalho AC (2019) A meta-learning recommender system for hyperparameter tuning: predicting when tuning improves svm classifiers. Inf Sci 501:193–221

    Google Scholar 

  • Mohan A, Poobal S (2018) Crack detection using image processing: a critical review and analysis. Alex Eng J 57(2):787–798

    Google Scholar 

  • Montgomery DC (2017) Design and analysis of experiments, 9th edn. Wiley, New York

    Google Scholar 

  • Munawar HS, Hammad AW, Haddad A, Soares CAP, Waller ST (2021) Image-based crack detection methods: a review. Infrastructures 6(8):115

    Google Scholar 

  • Nan Y, Ju J, Hua Q, Zhang H, Wang B (2022) A-mobilenet: an approach of facial expression recognition. Alex Eng J 61(6):4435–4444

    Google Scholar 

  • Ottoni ALC, Nepomuceno EG, de Oliveira MS, de Oliveira DCR (2020) Tuning of reinforcement learning parameters applied to sop using the Scott–Knott method. Soft Comput 24:4441–4453

    Google Scholar 

  • Ottoni ALC, Amorim RM, Novo MS, Costa DB (2023) Tuning of data augmentation hyperparameters in deep learning to building construction image classification with small datasets. Int J Mach Learn Cybern 14:171–186

    Google Scholar 

  • Ottoni ALC, Novo MS, Costa DB (2023) Hyperparameter tuning of convolutional neural networks for building construction image classification. Vis Comput 39(3):847–861

    Google Scholar 

  • Özgenel Ç F (2019) Concrete crack images for classification, v2 edition. Mendeley Data

  • Özgenel Ç F, Sorguç AG (2018) Performance comparison of pretrained convolutional neural networks on crack detection in buildings. In: Isarc. proceedings of the international symposium on automation and robotics in construction, vol 35. IAARC Publications, pp 1–8

  • Park S, Bang S, Kim H, Kim H (2019) Patch-based crack detection in black box images using convolutional neural networks. J Comput Civ Eng 33(3):04019017

    Google Scholar 

  • Park H, Nam Y, Kim J-H, Choo J (2021) Hypertendril: visual analytics for user-driven hyperparameter optimization of deep neural networks. IEEE Trans Vis Comput Graph 27(2):1407–1416

    Google Scholar 

  • Prakash AJ, Prakasam P (2022) An intelligent fruits classification in precision agriculture using bilinear pooling convolutional neural networks. Vis Comput 1–17

  • R Core Team (2020) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna

  • Razali NM, Wah YB et al (2011) Power comparisons of Shapiro-Wilk, Kolmogorov-Smirnov, Lilliefors and Anderson-darling tests. J Stat Model Analyt 2(1):21–33

    Google Scholar 

  • Scott AJ, Knott M (1974) A cluster analysis method for grouping means in the analysis of variance. Biometrics 30(3):507–512

    MATH  Google Scholar 

  • Sejnowski TJ (2018) The deep learning revolution. MIT Press, Cambridge

    Google Scholar 

  • Shorten C, Khoshgoftaar T (2019) A survey on image data augmentation for deep learning. J Big Data 6(1)

  • Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: 3rd international conference on learning representations, ICLR 2015—conference track proceedings

  • Song C, Xu W, Wang Z, Yu S, Zeng P, Ju Z (2020) Analysis on the impact of data augmentation on target recognition for uav-based transmission line inspection. Complexity 2020

  • Tang H, Shi J, Lu X, Yin Z, Huang L, Jia D, Wang N (2020) Comparison of convolutional sparse coding network and convolutional neural network for pavement crack classification: a validation study. In: Journal of physics: conference series, p 012016. IOP Publishing

  • Tangudu V, Kakarla J, Venkateswarlu IB (2022) Covid-19 detection from chest x-ray using mobilenet and residual separable convolution block. Soft Comput 26(5):2197–2208

    Google Scholar 

  • Ünlü R, Kiriş R (2021) Detection of damaged buildings after an earthquake with convolutional neural networks in conjunction with image segmentation. Vis Comput 1–10

  • Wong C, Houlsby N, Lu Y, Gesmundo A (2018) Transfer learning with neural automl. Adv Neural Inf Process Syst 31

  • Yao Y, Tung S-TE, Glisic B (2014) Crack detection and characterization techniques—an overview. Struct Control Health Monit 21(12):1387–1413

    Google Scholar 

  • Zawad M, Shahriar R, Zawad M, Shahriar F, Rahman M, Priyom SN et al (2021) A comparative review of image processing based crack detection techniques on civil engineering structures. J Soft Comput Civ Eng 5(3):58–74

    Google Scholar 

  • Zeiler MD (2012) Adadelta: an adaptive learning rate method. arXiv:1212.5701

  • Zerouaoui H, Idri A (2022) Deep hybrid architectures for binary classification of medical breast cancer images. Biomed Signal Process Control 71:103226

    Google Scholar 

  • Zhang X, Wang X (2020) An effective bridge cracks classification method based on machine learning. In: Proceedings of the 2020 4th international conference on electronic information technology and computer engineering, pp 790–794

  • Zhang A, Wang KC, Li B, Yang E, Dai X, Peng Y, Fei Y, Liu Y, Li JQ, Chen C (2017) Automated pixel-level pavement crack detection on 3d asphalt surfaces using a deep-learning network. Comput Aided Civ Infrastruct Eng 32(10):805–819

    Google Scholar 

  • Zhang Y, Zheng J, Sun W, Shan L (2020) Image recognition method of building wall cracks based on feature distribution. Soft Comput 24(11):8285–8294

    Google Scholar 

  • Zhou S, Song W (2020) Deep learning-based roadway crack classification using laser-scanned range images: a comparative study on hyperparameter selection. Autom Constr 114

  • Zimmer L, Lindauer M, Hutter F (2021) Auto-pytorch: multi-fidelity metalearning for efficient and robust autodl. IEEE Trans Pattern Anal Mach Intell 43(9):3079–3090

    Google Scholar 

Download references

Acknowledgements

The authors are grateful to FAPESB, CAPES (Finance Code 001), CNPq, UFBA and UFRB.

Funding

This study was financed in part by the Coordenação de Aperfeicoamento de Pessoal de Nível Superior - Brazil (CAPES) - Finance Code 001 and Conselho Nacional de DesenvolvimentoCientífico eTecnológico (CNPq).

Author information

Authors and Affiliations

  1. Technologic and Exact Center, Federal University of Recôncavo da Bahia, Cruz das Almas, Brazil

    André Luiz Carvalho Ottoni

  2. Department of Electrical and Computer Engineering, Federal University of Bahia, Salvador, Brazil

    Artur Moura Souza & Marcela Silva Novo

Authors
  1. André Luiz Carvalho Ottoni
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Artur Moura Souza
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Marcela Silva Novo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to André Luiz Carvalho Ottoni.

Ethics declarations

Conflict of interest

All the authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ottoni, A.L.C., Souza, A.M. & Novo, M.S. Automated hyperparameter tuning for crack image classification with deep learning. Soft Comput 27, 18383–18402 (2023). https://doi.org/10.1007/s00500-023-09103-x

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-023-09103-x

Keywords

Search

Navigation