A New Deep Learning Based Damage Classification Pipeline for Car Glass
Year 2025,
Volume: 11 Issue: 3, 210 - 223, 30.09.2025
Ömer Küllü
,
Anıl Çelik
,
Pınar Ece Aktan Hatipoğlu
,
Mehmet Kıvılcım Keleş
Abstract
Intelligent damage evaluation is a popular domain of applied Artificial Intelligence
(AI) in the insurance industry. Car glass damage is a common insurance claim. Accurately
identifying the nature of glass damage is essential, as it directly affects the decision between
repair and replacement, which has different safety and cost implications. This distinction
is crucial to ensure vehicle safety and effective claim processing. This paper proposes a
deep learning (DL) enhanced approach to reduce the claim process time by automatically
detecting damage in car glass. The primary objective of this study is to assess whether
glass damage is suitable for repair or necessitates total replacement. Owing to variations in
the image zoom levels for damaged glass, our method incorporates a branched pathway to
handle these differences effectively. Our pipeline employs both classification and segmentation
methods. The proposed approach begins by filtering the images. Based on the results, the
image is fed directly to the damage classification or subjected to further processing before
classification. Furthermore, ensemble and fusion techniques were employed to improve overall
efficiency. The ensemble-based strategy achieved an F1 score of 0.99 in damage classification,
outperforming other approaches.
Ethical Statement
No approval from the Board of Ethics is required.
References
-
P. M. Kyu, K. Woraratpanya, Car damage detection and classification, in: Proceedings of the
11th International Conference on Advances in Information Technology, Bangkok, 2020, pp. 1–6.
-
M. Parhizkar, M. Amirfakhrian, Car detection and damage segmentation in the real scene using a
deep learning approach, International Journal of Intelligent Robotics and Applications 6 (2) (2022)
231–245.
-
A. Guha, D. Samanta, Hybrid approach to document anomaly detection: An application to facilitate
RPA in title insurance, International Journal of Automation and Computing 18 (1) (2021) 55–72.
-
B. Benedek, C. Ciumas, B. Z. Nagy, Automobile insurance fraud detection in the age of big data –
a systematic and comprehensive literature review, Journal of Financial Regulation and Compliance
30 (4) (2022) 503–523.
-
H. Xia, Y. Zhou, Z. Zhang, Auto insurance fraud identification based on a CNN-LSTM fusion deep
learning model, International Journal of Ad Hoc and Ubiquitous Computing 39 (1-2) (2022) 37.
-
R. Van Ruitenbeek, S. Bhulai, Convolutional neural networks for vehicle damage detection, Machine
Learning with Applications 9 (2022) 100332.
-
K. Patil, M. Kulkarni, A. Sriraman, S. Karande, Deep learning based car damage classification, in:
2017 16th IEEE International Conference on Machine Learning and Applications, Cancun, 2017,
pp. 50–54.
-
L. Li, K. Ono, C.-K. Ngan, A deep learning and transfer learning approach for vehicle damage
detection, The International FLAIRS Conference Proceedings 34 (1) (2021) 6 pages.
-
T. Ojala, M. Pietik¨ainen, D. Harwood, A comparative study of texture measures with classification
based on featured distributions, Pattern Recognition 29 (1) (1996) 51–59.
-
A. Ramirez Rivera, J. Rojas Castillo, O. Oksam Chae, Local directional number pattern for face
analysis: Face and expression recognition, IEEE Transactions on Image Processing 22 (5) (2013)
1740–1752.
-
Q. Zhang, X. Chang, S. B. Bian, Vehicle-damage-detection segmentation algorithm based on
improved mask RCNN, IEEE Access 8 (2020) 6997–7004.
-
D. Mallios, L. Xiaofei, N. McLaughlin, J. M. D. Rincon, C. Galbraith, R. Garland, Vehicle damage
severity estimation for insurance operations using in-the-wild mobile images, IEEE Access 11
(2023) 78644–78655.
-
M. Dwivedi, H. S. Malik, S. N. Omkar, E. B. Monis, B. Khanna, S. R. Samal, A. Tiwari, A. Rathi,
Deep learning-based car damage classification and detection, in: N. N. Chiplunkar, T. Fukao (Eds.),
Advances in Artificial Intelligence and Data Engineering, Vol. 1133 of Advances in Intelligent
Systems and Computing, Springer Nature Singapore, Singapore, 2021, pp. 207–221.
-
J. Redmon, A. Farhadi, YOLOv3: An incremental improvement (2018),
https://arxiv.org/abs/1804.02767, Accessed 3 Mar 2025.
-
X. Wang, W. Li, Z. Wu, CarDD: A new dataset for vision-based car damage detection, IEEE
Transactions on Intelligent Transportation Systems 24 (7) (2023) 7202–7214.
-
J. Dai, H. Qi, Y. Xiong, Y. Li, G. Zhang, H. Hu, Y. Wei, Deformable convolutional networks
(2017), https://arxiv.org/abs/1703.06211, Accessed 3 Mar 2025.
-
M. Tan, Q. V. Le, EfficientNetV2: Smaller models and faster training (2021),
https://arxiv.org/abs/2104.00298, Accessed 3 Mar 2025.
-
M. Tan, Q. V. Le, EfficientNet: Rethinking model scaling for convolutional neural networks (2019),
https://arxiv.org/abs/1905.11946, Accessed 3 Mar 2025.
-
O. Ronneberger, P. Fischer, T. Brox, U-Net: Convolutional networks for biomedical image
segmentation, in: N. Navab, J. Hornegger, W. M. Wells, A. F. Frangi (Eds.), Medical Image
Computing and Computer-Assisted Intervention – MICCAI 2015, Vol. 9351 of Lecture Notes in
Computer Science, Springer International Publishing, Cham, 2015, pp. 234–241.
-
G. Huang, Z. Liu, L. van der Maaten, K. Q. Weinberger, Densely connected convolutional networks
(2016), https://arxiv.org/abs/1608.06993, Accessed 3 Mar 2025.
-
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, L.-C. Chen, MobileNetV2: Inverted residuals and
linear bottlenecks (2018), https://arxiv.org/abs/1801.04381, Accessed 3 Mar 2025.
-
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: 2016 IEEE
Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016, pp. 770–778.
-
H. Bao, L. Dong, S. Piao, F. Wei, BEiT: BERT pre-training of image transformers (2021),
https://arxiv.org/abs/2106.08254, Accessed 3 Mar 2025.
-
A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto,
H. Adam, MobileNets: Efficient convolutional neural networks for mobile vision applications
(2017), https://arxiv.org/abs/1704.04861, Accessed 3 Mar 2025.