SteelBlastQC: Shot-blasted Steel Surface Dataset with Interpretable Detection of Surface Defects

2025-04-29

AI Summary

To address the lack of standardized datasets and interpretable models for assessing sandblasted steel plate surface quality, this paper introduces the first industrial inspection-oriented annotated dataset comprising 1,654 RGB images (512×512), covering real-world defects including discoloration, weld marks, scratches, and rust, with binary labels: “paintable” or “requiring re-blasting.” We propose three interpretable discrimination methods: (i) end-to-end classification via CCT (Convolutional-Transformer hybrid), (ii) ResNet-50 feature extraction coupled with SVM classification and Grad-CAM-based localization, and (iii) CAE (Convolutional Autoencoder)-based anomaly detection with reconstruction error analysis. Our approach achieves, for the first time in sandblasting inspection, both high accuracy (95% classification accuracy) and visualizable defect localization. The dataset and benchmark code are publicly released, establishing a new paradigm and practical foundation for trustworthy, interpretable computer vision–based quality inspection in industrial settings.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Algorithmic accountability and transparency on the web

Abstract

Automating the quality control of shot-blasted steel surfaces is crucial for improving manufacturing efficiency and consistency. This study presents a dataset of 1654 labeled RGB images (512x512) of steel surfaces, classified as either"ready for paint"or"needs shot-blasting."The dataset captures real-world surface defects, including discoloration, welding lines, scratches and corrosion, making it well-suited for training computer vision models. Additionally, three classification approaches were evaluated: Compact Convolutional Transformers (CCT), Support Vector Machines (SVM) with ResNet-50 feature extraction, and a Convolutional Autoencoder (CAE). The supervised methods (CCT and SVM) achieve 95% classification accuracy on the test set, with CCT leveraging transformer-based attention mechanisms and SVM offering a computationally efficient alternative. The CAE approach, while less effective, establishes a baseline for unsupervised quality control. We present interpretable decision-making by all three neural networks, allowing industry users to visually pinpoint problematic regions and understand the model's rationale. By releasing the dataset and baseline codes, this work aims to support further research in defect detection, advance the development of interpretable computer vision models for quality control, and encourage the adoption of automated inspection systems in industrial applications.

Problem

• Automating quality control for shot-blasted steel surfaces
• Detecting surface defects like discoloration and corrosion
• Evaluating interpretable computer vision models for industrial inspection

Innovation

• Dataset with labeled RGB images for defect detection
• Evaluated transformer and SVM for classification
• Interpretable decision-making for industrial quality control