An Image Classification Method of Unbalanced Ship Coating Defects Based on DCCVAE-ACWGAN-GP
Source abstract
Abstract
Affected by the improper operation of the workers, environmental changes during drying and curing or the quality of the paint itself, diverse defects are produced during the process of ship painting. The traditional defect recognition method relies on expert knowledge or experience to detect defects, which is not conducive to ensuring the effectiveness of defect recognition. Therefore, this paper proposes an image generation and recognition model which is suitable for small samples. Based on a deep convolutional neural network (DCNN), the model combines a conditional variational autoencoder (DCCVAE) and auxiliary conditional Wasserstein GAN with gradient penalty (ACWGAN-GP) to gradually expand and generate various coating defect images for solving the overfitting problem due to unbalanced data. The DCNN model is trained based on newly generated image data and original image data so as to build a coating defect image classification model suitable for small samples, which is conducive to improving classification performance. The experimental results showed that our proposed model can achieve up to 92.54% accuracy, an F-score of 88.33%, and a G mean value of 91.93%. Compared with traditional data enhancement methods and classification algorithms, our proposed model can identify various defects in the ship painting process more accurately and consistently, which can provide effective theoretical and technical support for ship painting defect detection and has significant engineering research value and application prospects.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Imbalanced Data Classification Techniques · Non-Destructive Testing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical Engineering, Jiangsu University of Science and Technology, Zhenjiang 212100, China
Funding
Ministry of Industry and Information Technology High-Tech Ship Research Project · National Defense Basic Scientific Research Project · RO-RO Passenger Ship Efficient Construction Process and Key Technology Research
References (55)
Show source-provided references
1. Bu, H., Yuan, X., Niu, J., Yu, W., Ji, X., Lyu, Y., and Zhou, H. (2021). Ship Painting Process Design Based on IDBSACN-RF. Coatings, 11.10.3390/coatings11121458 ↗
2. Calculation of coating consumption quota for ship painting: A CS-GBRT approach
3. Coating matching recommendation based on improved fuzzy comprehensive evaluation and collaborative filtering algorithm10.1038/s41598-021-93628-4 ↗
4. Ma, H., and Lee, S. (2022). Smart System to Detect Painting Defects in Shipyards: Vision AI and a DeepLearning Approach. Appl. Sci., 12.10.3390/app12052412 ↗
5. Bu, H., Ji, X., Zhang, J., Lyu, Y., Pang, B., and Zhou, H. (2022). A Knowledge Acquisition Method of Ship Coating Defects Based on IHQGA-RS. Coatings, 12.10.3390/coatings12030292 ↗
6. Data-driven prediction of antiviral peptides based on periodicities of amino acid properties10.1016/B978-0-323-88506-5.50312-0 ↗
7. A novel feature fusion based deep learning framework for white blood cell classification
8. Ryan, M.C., and Mateen, R. (2020, January 18–20). Deep learning for image classification. Proceedings of the 2020 2nd International Conference on Information Technology and Computer Application (ITCA), Guangzhou, China.
9. Sadgrove, E.J., Greg, F., David, M., and David, W.L. (2021). The Segmented Colour Feature Extreme Learning Machine: Applications in Agricultural Robotics. Agronomy, 11.10.3390/agronomy11112290 ↗
10. Skin Cancer Classification Through Quantized Color Features and Generative Adversarial Network10.4018/IJACI.2021070104 ↗
11. Design of Artistic Creation Style Extraction Model Based on Color Feature Data
12. Compact Deep Color Features for Remote Sensing Scene Classification
13. An Improved Automatic Shape Feature Extraction Method Based on Template Matching10.1088/1742-6596/2095/1/012053 ↗
14. Integrated Method for Road Extraction: Deep Convolutional Neural Network Based on Shape Features and Images10.1166/jno.2021.3051 ↗
15. Rotational moment shape feature extraction and decision tree based discrimination of mild cognitive impairment conditions using mr image processing10.34107/YHPN9422.04228 ↗
16. Colour, Texture, and Shape Features based Object Recognition Using Distance Measures
17. Intelligent Image Diagnosis of Pneumoconiosis Based on Wavelet Transform-Derived Texture Features
18. Detection of subtle white matter lesions in MRI through texture feature extraction and boundary delineation using an embedded clustering strategy10.1038/s41598-022-07843-8 ↗
19. Alireza, R., Yasamin, J., and Ali, K. (2022). Explainable Ensemble Machine Learning for Breast Cancer Diagnosis Based on Ultrasound Image Texture Features. Forecasting, 4.10.3390/forecast4010015 ↗
20. Breast cancer detection in mammogram: Combining modified CNN and texture feature based approach
21. Determination of Hue Saturation Value (HSV) color feature in kidney histology image10.1088/1742-6596/2157/1/012020 ↗
22. Environmental-economic sustainability of hydrogen and ammonia fuels for short sea shipping operations10.1016/j.ijhydene.2024.01.058 ↗
23. Na, H.J., and Park, J.S. (2021). Accented Speech Recognition Based on End-to-End Domain Adversarial Training of Neural Networks. Appl. Sci., 11.10.3390/app11188412 ↗
24. A Review on Traditional Machine Learning and Deep Learning Models for WBCs Classification in Blood Smear Images
25. Imbalanced data classification: A KNN and generative adversarial networks-based hybrid approach for intrusion detection10.1016/j.future.2022.01.026 ↗
26. Du, C., Liu, P., and Zheng, M. (2022). Classification of Imbalanced Electrocardiosignal Data using Convolutional Neural Network. Comput. Methods Programs Biomed., 214.10.1016/j.cmpb.2021.106483 ↗
27. Deep Learning for Computer Vision: A Brief Review
28. Recent Trends in Deep Learning Based Natural Language Processing [Review Article]10.1109/MCI.2018.2840738 ↗
29. Estiri, S.N., Jalilvand, A.H., Naderi, S., Najafi, M.H., and Fazeli, M. (2022, January 24–25). A Low-Cost Stochastic Computing-based Fuzzy Filtering for Image Noise Reduction. Proceedings of the IEEE 13th International Green and Sustainable Computing Conference (IGSC), Pittsburgh, PA, USA.10.1109/IGSC55832.2022.9969358 ↗
30. Zhao, W., Qin, W., and Li, M. (2021, January 22–24). An Optimized Model based on Metric-Learning for Few-Shot Classification. Proceedings of the 33rd Chinese Control and Decision Conference (CCDC), Kunming, China.10.1109/CCDC52312.2021.9601665 ↗
31. Pattern Recognition of Travel Mobility in a City Destination: Application of Network Motif Analytics10.1177/00472875211024739 ↗
32. Liu, J., Zhang, K., Wu, S., Shi, H., Zhao, J., and Yao, D. (2022). An Investigation of a Multidimensional CNN Combined with an Attention Mechanism Model to Resolve Small-Sample Problems in Hyperspectral Image Classification. Remote Sens., 14.10.3390/rs14030785 ↗
33. A new dynamic model and transfer learning based intelligent fault diagnosis framework for rolling element bearings race faults: Solving the small sample problem10.1016/j.isatra.2021.03.042 ↗
34. Convolutional neural network for spectral–spatial classification of hyperspectral images10.1007/s00521-019-04371-x ↗
35. MWMOTE-Majority Weighted Minority Oversampling Technique for Imbalanced Data Set Learning10.1109/TKDE.2012.232 ↗
36. Quek. Data-Limited Modulation Classification with a CVAE-Enhanced Learning Model
37. A Survey on the Development of Image Data Augmentation
38. CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection10.1109/ACCESS.2020.2994762 ↗
39. Automated defect inspection system for metal surfaces based on deep learning and data augmentation
40. VGG16 for Plant Image Classification with Transfer Learning and Data Augmentation
41. Sohn, Y.K., Yan, X., and Lee, H. (2021, January 8–12). Learning structured output representation using deep conditional generative models. Proceedings of the 28th International Conference on Neural Information Processing Systems, Bali, Indonesia.
42. Wu, X., Feng, W., Guo, Y., and Wang, Q. (2021). Feature Learning for SAR Target Recognition with Unknown Classes by Using CVAE-GAN. Remote Sens., 13.10.3390/rs13183554 ↗
43. Synthesizing Multi-Contrast MR Images Via Novel 3D Conditional Variational Auto-Encoding GAN10.1007/s11036-020-01678-1 ↗
44. Multi-Constraint Adversarial Networks for Unsupervised Image-to-Image Translation
45. Christian, L., Lucas, T., Ferencr, H., Jose, C., Andrew, P., Alykhan, T., Johannes, T., Wang, Z., and Shi, W. (2017, January 21–26). Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.
46. Deep cycle autoencoder for unsupervised domain adaptation with generative adversarial networks10.1049/iet-cvi.2019.0304 ↗
47. Mapping a hazardous abandoned gypsum mine using self-potential, electrical resistivity tomography, and Frequency Domain Electromagnetic methods10.1016/j.jappgeo.2022.104771 ↗
48. Ngoc, T.T., Viet, H.T., Ngoc, B.N., and Ngai, M.C. (2019, January 14). An Improved Selfsupervised GAN via Adversarial Training. Proceedings of the Computer Vision and Pattern Recognition, Long Beach, CA, USA.
49. A single video superresolution GAN for multiple downsampling operators based on pseudo-inverse image formation models10.1016/j.dsp.2020.102801 ↗
50. Jang, Y., Sim, J., Yang, J., and Kwon, N.K. (2022). Improving heart rate variability information consistency in Doppler cardiogram using signal reconstruction system with deep learning for Contact-free heartbeat monitoring. Biomed. Signal Process Control., 76.10.1016/j.bspc.2022.103691 ↗
51. Zou, L., Zhang, H., Wang, C., Wu, F., and Gu, F. (2020). MW-ACGAN: Generating Multiscale High-Resolution SAR Images for Ship Detection. Sensors, 20.10.3390/s20226673 ↗
52. Using generative adversarial networks for improving classification effectiveness in credit card fraud detection
53. Augustus, O., Christopher, O., and Jonathon, S. (2017, January 20). Conditional Image Synthesis With Auxiliary Classifier GANs. Proceedings of the Computer Vision and Pattern Recognition, Honolulu, HI, USA.
54. Loss Functions of Generative Adversarial Networks (GANs): Opportunities and Challenges10.1109/TETCI.2020.2991774 ↗
55. Data augmentation for time series regression: Applying transformations, autoencoders and adversarial networks to electricity price forecasting10.1016/j.apenergy.2021.117695 ↗