Tire tread, as a primary feature of tires, presents a formidable challenge in reliable detection due to the vast variety of treads available and the scarcity of publicly available datasets. To address this issue, this paper introduces DCT-ResNet, a neural network designed for adaptive fusion of spatial and frequency domain features. This method overcomes dataset limitations through the use of generative networks and image enhancement techniques. Initially, the network captures spatial features using down-sampling layers and hidden layers. Concurrently, frequency domain features are extracted through the integration of Discrete Cosine Transform (DCT) and a specialized frequency domain network. The final step involves the use of a multi-head self-attention layer to achieve adaptive feature fusion, ensuring the reliable extraction of tire tread features. Experimental results highlight the effectiveness of the proposed approach. The DCT-ResNet network achieves impressive classification accuracies of 99% on the tire tread dataset and 97% on the CIFAR-10 dataset. Additionally, the network demonstrates a level of pattern similarity detection comparable to expert judgments. In adversarial testing, the data augmentation significantly enhances the network’s robustness, allowing DCT-ResNet to outperform other methods in resistance to interference. Consequently, the method presented in this paper holds substantial practical significance for the high-reliability detection of tire treads.
LiuYYanHLimKP. Study on rotation-invariant texture feature extraction for tire pattern retrieval. Multidimens Syst Signal Process2017; 28(2): 757–770.
2.
HuangDHuWWangY, et al. Recognition of tire tread patterns based on Gabor wavelets and support vector machine. In: PanJChenSNguyenTN (eds) Computational Collective Intelligence Technologies and Applications. Kaohsiung, Taiwan: Springer. 2010, pp. 92–101.
3.
LiuYLiZGaoZM. An improved texture feature extraction method for tyre tread patterns. In: SunCFangFZhouZH, et al. (eds) Intelligence Science and Big Data Engineering. Beijing, China: Springer. 2013, pp. 705–713.
4.
JiaSMaJ. Tire pattern retrieval based on wavelet transform and gray level co-occurrence matrix. Comput Meas Control2016; 24(6): 210–213.
5.
WangSLiuYLiD, et al. An improved SIFT feature extraction method for tyre tread patterns retrieval. In: 2014 Seventh international symposium on computational intelligence and design, 2014, vol. 1, pp. 539–543. DOI: 10.1109/ISCID.2014.276.
6.
YanHLiuY. An improved texture feature extraction method based on Radon transform. In: 2014 Seventh international symposium on computational intelligence and design, 2014, vol. 1, pp. 481–485. DOI: 10.1109/ISCID.2014.101.
7.
LiuYZhangSWangF, et al. Wavelet-energy-weighted local binary pattern analysis for tire tread pattern classification. In: 2019 3rd International conference on imaging, signal processing and communication (ICISPC), 2019, pp. 90–95. DOI: 10.1109/ICISPC.2019.8935658.
8.
LiuYZhangSLiDX, et al. An effective tread pattern image classification algorithm based on transfer learning. In: Proceedings of the 3rd international conference on multimedia systems and signal processing, 2018, pp. 51–55. DOI: 10.1145/3220162.3220174.
9.
LiuYZhangSFanJL. Tread pattern image classification with feature fusion based on transfer learning. Computer Engineering and Design2019; 40(05): 1401–1406. DOI: 10.16208/j.issn1000-7024.2019.05.037.
10.
ChenHHanY. Tire classification based on attention mechanism and transfer learning. SoftwareX2022; 43(6): 65–69.
11.
LiuYLeiYRashidSF. Graph convolution network with node feature optimization using cross attention for few-shot learning. In: Proceedings of the 2nd ACM international conference on multimedia in Asia, 2021, pp. 1–7. https://doi.org/10.1145/3444685.3446278
QiangYShengCYinD. Method of tire pattern image retrieval based on wavelet transform and Siamese network. In: Proceedings of the 2020 international conference on aviation safety and information technology, 2020, pp. 587–592. DOI: 10.1145/3434581.3434690.
14.
YanJZhuYLiangZ, et al. Tire pattern classification based on few-shot learning. In: 2021 IEEE international conference on multimedia & expo workshops (ICMEW), 2021, pp. 1–7. DOI: 10.1109/ICMEW53276.2021.9455988.
15.
CaiCLinM. Tire pattern similarity detection based on template matching and LBP. In: 2019 3rd international conference on electronic information technology and computer engineering (EITCE), 2019, pp. 419–423. DOI: 10.1109/EITCE47263.2019.9095051.
16.
HonglingLYudeDHengD, et al. A feature-based method for tire pattern similarity detection. Proc IMechE, Part D: J Automob Eng2023; 237(10-11): 2539–2552.
17.
LiHDongYHuangZ, et al. Similarities detection and analysis of tire patterns based on similarity theory. China Mech Eng2021; 32(14); 1646–1652.
18.
GoodfellowIPouget-AbadieJMirzaM, et al. Generative Adversarial Nets. In: Proceedings of the 27th international conference on neural information processing systems (NIPS), 2014; vol. 2, pp. 2672–2680. DOI: 10.5555/2969033.2969125.
19.
ArjovskyMChintalaSBottouL. Wasserstein generative adversarial networks. In: Proceedings of the 34th international conference on machine learning (ICML), 2017, vol. 70, pp. 214–223. DOI: 10.5555/3305381.3305404.
20.
ZhangHCisseMDauphinYN, et al. Mixup: Beyond empirical risk minimization. arXiv pre-print arXiv: 1710.09412, 2018. Available at: http://arxiv.org/abs/1710.09412
21.
GulrajaniIAhmedFArjovskyM, et al. Improved training of Wasserstein GANs. In: NIPS’17: Proceedings of the 31st international conference on neural information processing systems (NIPS), 2017, pp. 5769–5779. DOI: 10.5555/3295222.3295327.
22.
ZhuJYParkTIsolaP, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE international conference on computer vision (ICCV), 2017, pp. 2242–2251. DOI: 10.1109/ICCV.2017.244.
23.
YunSHanDChunS, et al. CutMix: Regularization strategy to train strong classifiers with localizable features. In: 2019 IEEE/CVF international conference on computer vision (ICCV), 2019, pp. 6022–6031. DOI: 10.1109/ICCV.2019.00612.
24.
KrizhevskyASutskeverIHintonGE. ImageNet classification with deep convolutional neural networks. In: Communications of the ACM2017, vol. 60, pp. 84–90. DOI: 10.1145/3065386.
25.
GoyalABengioY. Inductive biases for deep learning of higher-level cognition. Proc R Soc A Math Phys Eng Sci2022; 478(2266): 1–35.
26.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), 2016, pp. 770–778. DOI: 10.1109/CVPR.2016.90.
27.
ChattopadhayASarkarAHowladerP, et al. Grad-CAM++: Generalized gradient-based visual explanations for deep convolutional networks. In: 2018 IEEE winter conference on applications of computer vision (WACV), 2018, pp. 839–847. DOI: 10.1109/WACV.2018.00097.
28.
XuKQinMSunF, et al. Learning in the frequency domain. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2020, pp. 1737–1746. DOI: 10.1109/CVPR42600.2020.00181.
29.
HuJShenLSunG. Squeeze-and-excitation networks. In: 2018 IEEE/CVF conference on computer vision and pattern recognition, 2018, pp. 7132–7141. DOI: 10.1109/CVPR.2018.00745.
30.
BahdanauDChoKBengioY. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv: 1409.0473, 2016. DOI: 10.48550/arXiv.1409.0473.
31.
VaswaniAShazeerNParmarN, et al. Attention is all you need. In: Proceedings of the 31st international conference on neural information processing systems (NIPS), 2017, pp. 6000–6010. DOI: 10.5555/3295222.3295349.
32.
ChenWLiuYKiraZ, et al. A closer look at few-shot classification. arXiv preprint arXiv:1904.04232, 2020. DOI: 10.48550/arXiv.1904.04232.
33.
DhillonGChaudhariPRavichandranA, et al. A baseline for few-shot image classification. arXiv preprint arXiv: 1909.02729, 2020. DOI: 10.48550/arXiv.1909.02729.
Ministry of Public Security of China CIIP Lab. Key lab of electronic information processing with applications in crime scene investigation. CIIP Data, 2019. Available at: http://www.xuptciip.com.cn/show.html?database-lthhhw (accessed 10 December 2023).
36.
HeKChenXXieS, et al. Masked autoencoders are scalable vision learners. In: 2022 IEEE/CVF conference on computer vision and pattern recognition (CVPR), 2022, pp. 15979–15988. DOI: 10.1109/CVPR52688.2022.01553.
37.
LiuYGeY. Tire tread pattern image classification based on SVM, CNN and transfer learning. J Xi’an Univ Post Telecommun2018; 23(03): 38–44. DOI: 10.13682/j.issn.2095-6533.2018.03.006.
