An Improved Small Defect Classification System Using Image Patching Methodology on Aluminum Car Doors
Open Access
- 5 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 3177-3191
Abstract
Small surface defects in automotive manufacturing such as micro-cracks, springbacks, and minor deformations typically appear in highly curved or reflective regions of large and complex components. Although recent Artificial Intelligence (AI)–based visual inspection systems have improved classification, existing whole-image classification methods still struggle to identify subtle or localized defects that occupy only a small portion of the image. These subtle defects occupy only small and localized regions, analyzing the entire image as a single representation often leads to missed detections and insufficient sensitivity. To address these issues, we propose a small defect classification system using patch-based methodology. The approach divides each car-door image into spatial windows, enabling localized inspection of subtle defects that would otherwise be masked in full-image representations. First, Each window is processed using an enhanced Large Kernel Attention (LKA)-based ResNet50 backbone, where the LKA mechanism increases the effective receptive field and improves small-defect discriminability within each patch. Second, To overcome the limitation of independent patch predictions, we introduce a Self-Attention-Based Multi-Layer Perceptron (MLP) Aggregator that learns inter-patch dependencies and adaptively fuses window-level outputs into a robust whole-image decision, ensuring that cross-window defects are not overlooked. Experimental results showthat the combination of localized patch inspection, LKA-enhanced feature extraction, and self-attention based MLP aggregation yields superior performance, achieving 95% accuracy and 95% F1-score. These results confirm the effectiveness of the proposed image patching methodology as a reliable and scalable solution for industrial small-defect detection.Keywords
Funding Information
- Institute of Information and Communications Technology Planning and Evaluation (IITP)-Innovative Human Resource Development for Local Intellectualization Program
- Korean Government [Ministry of Science and ICT (MSIT)], Republic of Korea (IITP-2025-RS-2022-00156287 (34%))
- IITP through the Artificial Intelligence Convergence Innovation Human Resources Development
- Korean government (IITP-2025-RS-2023-00256629 (33%))
- Korea Institute of Planning and Evaluation for Technology in Food, Agriculture, and Forestry (IPET) through the Agriculture and Food Convergence Technologies Program for Research Manpower Development
- Ministry of Agriculture, Food, and Rural Affairs (RS-2024-00397026 (33%))
This publication has 64 references indexed in Scilit:
- Real-time weld seam feature extraction in construction sitesAutomation in Construction, 2024
- Visual attention networkComputational Visual Media, 2023
- Surface defect detection and classification of steel using an efficient Swin TransformerAdvanced Engineering Informatics, 2023
- A Study of Dimensionality Reduction in GLCM Feature-Based Classification of Machined Surface ImagesArabian Journal for Science and Engineering, 2023
- Defect-aware transformer network for intelligent visual surface defect detectionAdvanced Engineering Informatics, 2023
- Pavement anomaly detection based on transformer and self-supervised learningAutomation in Construction, 2022
- Vision transformer-based autonomous crack detection on asphalt and concrete surfacesAutomation in Construction, 2022
- Cas-VSwin transformer: A variant swin transformer for surface-defect detectionComputers in Industry, 2022
- Detection of fabric defects with intertwined frame vector feature extractionAlexandria Engineering Journal, 2022
- Improved faster R-CNN for fabric defect detection based on Gabor filter with Genetic Algorithm optimizationComputers in Industry, 2022