A Curated Dataset and Deep Learning Approach for Minor Dent Detection in Vehicles

2025-08-21

AI Summary

To address the challenge of detecting subtle surface dents on vehicles—often imperceptible to manual inspection—this paper proposes a deep learning–based automated detection method. We construct the first real-world, annotated dataset of vehicle surface micro-defects, featuring diverse lighting conditions, multi-view angles, and complex textures. A lightweight, customized model, YOLOv8m-t42, is designed with integrated real-time data augmentation to enhance robustness for small-object detection. Performance is rigorously evaluated using mAP@0.5, precision, recall, and F1-score. Experimental results demonstrate strong performance: 0.86 precision, 0.84 recall, 0.85 F1-score, and 0.60 mAP@0.5, with low inference latency suitable for in-vehicle real-time deployment. Our key contributions include: (1) the first dedicated, publicly available dataset for vehicle body micro-dent detection; (2) a YOLOv8-based lightweight architecture specifically optimized for small-target detection; and (3) a validated end-to-end industrial solution successfully deployed in practical automotive quality inspection scenarios.

Technology Category

• Computer Vision: Object Detection & Categorization
• Machine Learning: Hardware-aware ML
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Conventional car damage inspection techniques are labor-intensive, manual, and frequently overlook tiny surface imperfections like microscopic dents. Machine learning provides an innovative solution to the increasing demand for quicker and more precise inspection methods. The paper uses the YOLOv8 object recognition framework to provide a deep learning-based solution for automatically detecting microscopic surface flaws, notably tiny dents, on car exteriors. Traditional automotive damage inspection procedures are manual, time-consuming, and frequently unreliable at detecting tiny flaws. To solve this, a bespoke dataset containing annotated photos of car surfaces under various lighting circumstances, angles, and textures was created. To improve robustness, the YOLOv8m model and its customized variants, YOLOv8m-t4 and YOLOv8m-t42, were trained employing real-time data augmentation approaches. Experimental results show that the technique has excellent detection accuracy and low inference latency, making it suited for real-time applications such as automated insurance evaluations and automobile inspections. Evaluation parameters such as mean Average Precision (mAP), precision, recall, and F1-score verified the model's efficacy. With a precision of 0.86, recall of 0.84, and F1-score of 0.85, the YOLOv8m-t42 model outperformed the YOLOv8m-t4 model (precision: 0.81, recall: 0.79, F1-score: 0.80) in identifying microscopic surface defects. With a little reduced mAP@0.5:0.95 of 0.20, the mAP@0.5 for YOLOv8m-t42 stabilized at 0.60. Furthermore, YOLOv8m-t42's PR curve area was 0.88, suggesting more consistent performance than YOLOv8m-t4 (0.82). YOLOv8m-t42 has greater accuracy and is more appropriate for practical dent detection applications, even though its convergence is slower.

Problem

• Automating detection of microscopic dents on vehicle surfaces
• Overcoming manual inspection limitations for tiny imperfections
• Enabling real-time automotive damage assessment using deep learning

Innovation

• YOLOv8 deep learning for microscopic dent detection
• Custom dataset with annotated images under varied conditions
• Real-time data augmentation enhances model robustness and accuracy