.svg){kind=logo}
IMBALANCED MULTICLASS TRAFFIC SIGN IMAGES CLASSIFICATION BASED ON MINORITY OVERSAMPLING AND CONVOLUTIONAL NEURAL NETWORKS
Keywords:
imbalanced data, traffic sign recognition, oversampling, classification, convolutional neural networks.DOI:
https://doi.org/10.17654/0972361722089Abstract
Solving a multi-class classification task using an imbalanced database of patterns of high dimension is difficult due to the curse-of-dimensionality and the bias of the training toward the majority classes. This work aims to show the disadvantage of imbalanced data in an image classification task but also to present a strategy called “manual technique” for oversampling minority classes in a Chinese traffic sign recognition database. The classes of minority instances are oversampled by applying some transformations to these instances until they have the same size of the majority classes. The classification is done by using sequential convolutional neural networks and two models are compared by using, respectively, the imbalanced database and the oversampled (balanced) one. The results show an improvement of accuracy on the global classification and in particular on the oversampled classes.
Received: October 3, 2022
Accepted: November 28, 2022
References
D. Ramyachitra and P. Manikandan, Imbalanced dataset classification and solutions: a review, International Journal of Computing and Business Research (IJCBR) 5(4) (2014), 1-29.
K. Simonyan and A. Zisserman, Very deep convolutional networks for large scale image recognition 2015. arXiv preprint, https://arxiv.org/abs/1409.1556.
A. Krizhevsky, I. Sutskever and G. E. Hinton, Imagenet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, eds., Curran Associates, Inc., 2012, pp. 1097-1105.
Y. Yu, J. Li, C. Wen, H. Guan, H. Luo and C. Wang, Bag-of visual-phrases and hierarchical deep models for traffic sign detection and recognition in mobile laser scanning data, ISPRS Journal of Photogrammetry and Remote Sensing 113 (2016), 106-123.
K. Polat, Similarity-based attribute weighting methods via clustering algorithms in the classification of imbalanced medical datasets, Neural Comput. Appl. 30 (2018), 987-1013.
W. Han, Z. Huang, S. Li and Y. Jia, Distribution-sensitive unbalanced data oversampling method for medical diagnosis, J. Med. Syst. 43 (2019), 39.
H. He and E. A. Garcia, Learning from imbalanced data, IEEE Transactions on Knowledge and Data Engineering 21(9) (2009), 1263-1284.
G. Menardi and N. Torelli, Training and assessing classification rules with imbalanced data, Data Mining and Knowledge Discovery 28(1) (2014), 92-122.
E. C. Orenstein, O. Beijbom, E. E. Peacock and H. M. Sosik, WHOI-plankton- A large scale fine grained visual recognition benchmark dataset for plankton classification, 2015. arXiv preprint, https://arxiv.org/abs/1510.00745.
H. Lee, M. Park and J. Kim, Plankton classification on imbalanced large scale database via convolutional neural networks with transfer learning, 2016 IEEE International Conference on Image Processing (ICIP) 2016, pp. 3713-3717.
Z. Fan, Y. Wu, C. Zhou, X. Zhang and Z. Tao, Class-imbalanced voice pathology detection and classification using fuzzy cluster oversampling method, Applied Sciences 11(8) (2021), 3450.
Y. Wu, Z. Li, Y. Chen, K. Nai and J. Yuan, Real-time traffic sign detection and classification towards real traffic scene, Multimedia Tools and Applications 79(25) (2020), 18201-18219.
H. Kaur, H. S. Pannu and A. K. Malhi, A systematic review on imbalanced data challenges in machine learning: applications and solutions, ACM Computing Surveys (CSUR) 52(4) (2019), 1-36.
H. Jegierski and S. Saganowski, An “outside the box” solution for imbalanced data classification, IEEE Access 8 (2020), 125191-125209.
Chinese Traffic Sign Recognition Database,
Available online: http://www.nlpr.ia.ac.cn/pal/trafficdata/recognition.html
(accessed on 03/07/2022).
I. B. Sani, I. S. Zakari, M. M. Idrissa and D. Abdourahimoun, Machine learning based classification of traffic signs images from a robot-car, IEEE Access (proceedings of the IEEE Multi-conference on Natural and Engineering Sciences for Sahel’s Sustainable Development (MNE3SD)), 2022, pp. 1-6.
B. Kumar, 10 Techniques to deal with Imbalanced Classes in Machine Learning, Available online: https://www.analyticsvidhya.com/blog/2020/07/10-techniques-to-deal-with-class-imbalance-in-machine-learning/ (accessed on 02/08/2022).
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Pushpa Publishing House, Prayagraj, India
This work is licensed under a Creative Commons Attribution 4.0 International License.
____________________________
Attribution: Credit Pushpa Publishing House as the original publisher, including title and author(s) if applicable.
No Derivatives: Modifying or creating derivative works not allowed without written permission.
Contact Pushpa Publishing House for more info or permissions.
Journal Impact Factor: 
