A Self-Supervised Model Based on CutPaste-Mix for Ductile Cast Iron Pipe Surface Defect Classification
Open Access
Abstract
Online surface inspection systems have gradually found applications in industrial settings. However, the manual effort required to sift through a vast amount of data to identify defect images remains costly. This study delves into a self-supervised binary classification algorithm for addressing the task of defect image classification within ductile cast iron pipe (DCIP) images. Leveraging the CutPaste-Mix data augmentation strategy, we combine defect-free data with enhanced data to input into a deep convolutional neural network. Through Gaussian Density Estimation, we compute anomaly scores to achieve the classification of abnormal regions. Our approach has been implemented in real-world scenarios, involving equipment installation, data collection, and experimentation. The results demonstrate the robust performance of our method, in both the DCIP image dataset and practical field application, achieving an impressive 99.5 AUC (Area Under Curve). This presents a cost-effective means of providing data support for subsequent DCIP surface inspection model training.Keywords
Funding Information
- Beijing Science and Technology Planning Project (Z221100005822012, 2021YFB3202403)
- Key Technologies Research and Development Program of China (Z221100005822012, 2021YFB3202403)
This publication has 30 references indexed in Scilit:
- Probabilistic failure investigation of small diameter cast iron pipelines for water distributionEngineering Failure Analysis, 2020
- Surface defect classification of steels with a new semi-supervised learning methodOptics and Lasers in Engineering, 2019
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Information Processing in Medical Imaging2017
- The locally Gaussian density estimator for multivariate dataStatistics and Computing, 2016
- Artificial Neural Networks and Machine Learning – ICANN 2011Lecture Notes in Computer Science, 2011
- AUC: a misleading measure of the performance of predictive distribution modelsGlobal Ecology and Biogeography, 2007
- Variable Kernel Density EstimationThe Annals of Statistics, 1992
- Parametric generalized Gaussian density estimationThe Journal of the Acoustical Society of America, 1989