An Image Generation Method of Unbalanced Ship Coating Defects Based on IGASEN-EMWGAN
Open Access
Abstract
During the process of ship coating, various defects will occur due to the improper operation by the workers, environmental changes, etc. The special characteristics of ship coating limit the amount of data and result in the problem of class imbalance, which is not conducive to ensuring the effectiveness of deep learning-based models. Therefore, a novel hybrid intelligent image generation algorithm called the IGASEN-EMWGAN model for ship painting defect images is proposed to tackle the aforementioned limitations in this paper. First, based on a subset of imbalanced ship painting defect image samples obtained by a bootstrap sampling algorithm, a batch of different base discriminators was trained independently with the algorithm parameter and sample perturbation method. Then, an improved genetic algorithm based on the simulated annealing algorithm is used to search for the optimal subset of base discriminators. Further, the IGASEN-EMWGAN model was constructed by fusing the base discriminators in this subset through a weighted integration strategy. Finally, the trained IGASEN-EMWGAN model is used to generate new defect images of the minority classes to obtain a balanced dataset of ship painting defects. The extensive experimental results are conducted on a real unbalanced ship coating defect database and show that, compared with the baselines, the values of the ID and FID scores are significantly improved by 4.92% and decreased by 7.29%, respectively, which prove the superior effectiveness of the proposed model in this paper.Keywords
Funding Information
- Ministry of Industry and Information Technology High-Tech Ship Research Project (MC-202003-Z01-02, JCKY2021414B011, CJ07N20, 44)
- National Defense Basic Scientific Research Project (MC-202003-Z01-02, JCKY2021414B011, CJ07N20, 44)
- RO-RO Passenger Ship Efficient Construction Process and Key Technology Research (MC-202003-Z01-02, JCKY2021414B011, CJ07N20, 44)
- Intelligent Methanol-Fueled New Energy Ship R&D Project (MC-202003-Z01-02, JCKY2021414B011, CJ07N20, 44)
This publication has 67 references indexed in Scilit:
- Using generative adversarial networks for improving classification effectiveness in credit card fraud detectionInformation Sciences, 2019
- Effective data generation for imbalanced learning using conditional generative adversarial networksExpert Systems with Applications, 2018
- A novel hierarchical selective ensemble classifier with bioinformatics applicationArtificial Intelligence in Medicine, 2017
- Analysis of Hull Coating Renewal in Ship RepairingJournal of Ship Production and Design, 2017
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network2017
- Comparative analysis of genetic crossover operators in knapsack problemJournal of Applied Sciences and Environmental Management, 2016
- Development of paint area estimation software for ship compartments and structuresInternational Journal of Naval Architecture and Ocean Engineering, 2016
- Machine Learning for Evolution Strategies2016
- LibD3C: Ensemble classifiers with a clustering and dynamic selection strategyNeurocomputing, 2014
- MWMOTE--Majority Weighted Minority Oversampling Technique for Imbalanced Data Set LearningIEEE Transactions on Knowledge and Data Engineering, 2012