A High-Quality GAN With Data Augmentation for Aircraft Skin Defect Detection Under Limited Data
- 28 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
Abstract
Aircraft skin defect detection is one of the crucial steps in the regular maintenance. However, the performance of defect detection algorithms is limited by insufficient data, which makes a challenge for automated defect detection of aircraft skin. Although image generation techniques relieve the problem of insufficient defect data, they are not effective under the condition of limited original data. To tackle this issue, this paper proposes an image generation method that can obtain high-quality images of aircraft skin defects under limited data. Firstly, high-frequency skip connection (HSC) is performed in the generator to enhance the utilization of frequency information. Moreover, high-frequency features fusion blocks (HFFB) are utilized to effectively improve the high-frequency awareness of the discriminator. Meanwhile, adaptive high-dimensional diffusion (AHD) is introduced into the discriminator, which can automatically adjust the diffusion intensity according to the degree of discriminator overfitting. Finally, an aircraft skin defect dataset is constructed and a Generation-Poisson blending data augmentation method is proposed. The mAP of YOLOX trained using the augmentation dataset can reach 78.55%, which is 5.27% higher than the original data. The proposed method is capable of generating realistic and diverse images of aircraft skin defects, which significantly enhances the precision of defect detection networks in various scenes.Keywords
Funding Information
- National Natural Science Foundation of China (61573185)
- Hui Yan Action of China (62502010224)
- Innovative Experiment Competition for Postgraduate Students of Nanjing University of Aeronautics and Astronautics
This publication has 31 references indexed in Scilit:
- Erasing-inpainting-based data augmentation using denoising diffusion probabilistic models with limited samples for generalized surface defect inspectionMechanical Systems and Signal Processing, 2023
- A data generation method with dual discriminators and regularization for surface defect detection under limited dataComputers in Industry, 2023
- A deeper generative adversarial network for grooved cement concrete pavement crack detectionEngineering Applications of Artificial Intelligence, 2023
- GrapeGAN: Unsupervised image enhancement for improved grape leaf disease recognitionComputers and Electronics in Agriculture, 2022
- Visual inspection of aircraft skin: Automated pixel-level defect detection by instance segmentationChinese Journal of Aeronautics, 2022
- Automatic Generation of Polyp Image using Depth Map for Endoscope DatasetProcedia Computer Science, 2021
- A semi-supervised convolutional neural network-based method for steel surface defect recognitionRobotics and Computer-Integrated Manufacturing, 2020
- Feature Pyramid Networks for Object Detection2017
- The Aircraft Skin Crack Inspection Based on Different-Source Sensors and Support Vector MachinesJournal of Nondestructive Evaluation, 2016
- A theory for multiresolution signal decomposition: the wavelet representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989