{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:40:22Z","timestamp":1773384022944,"version":"3.50.1"},"reference-count":19,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T00:00:00Z","timestamp":1728518400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Accurately classifying road signs is crucial for autonomous driving due to the high stakes involved in ensuring safety and compliance. As Convolutional Neural Networks (CNNs) have largely replaced traditional Machine Learning models in this domain, the demand for substantial training data has increased. This study aims to compare the performance of classical Machine Learning (ML) models and Deep Learning (DL) models under varying amounts of training data, particularly focusing on altered signs to mimic real-world conditions. We evaluated three classical models: Support Vector Machine (SVM), Random Forest, and Linear Discriminant Analysis (LDA), and one Deep Learning model: Convolutional Neural Network (CNN). Using the German Traffic Sign Recognition Benchmark (GTSRB) dataset, which includes approximately 40,000 German traffic signs, we introduced digital alterations to simulate conditions such as environmental wear or vandalism. Additionally, the Histogram of Oriented Gradients (HOG) descriptor was used to assist classical models. Bayesian optimization and k-fold cross-validation were employed for model fine-tuning and performance assessment. Our findings reveal a threshold in training data beyond which accuracy plateaus. Classical models showed a linear performance decrease under increasing alteration, while CNNs, despite being more robust to alterations, did not significantly outperform classical models in overall accuracy. Ultimately, classical Machine Learning models demonstrated performance comparable to CNNs under certain conditions, suggesting that effective road sign classification can be achieved with less computationally intensive approaches.<\/jats:p>","DOI":"10.3390\/info15100621","type":"journal-article","created":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T08:16:42Z","timestamp":1728548202000},"page":"621","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Sensitivity Analysis of Traffic Sign Recognition to Image Alteration and Training Data Size"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0884-576X","authenticated-orcid":false,"given":"Arthur","family":"Rubio","sequence":"first","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, IMT Mines Ales, Ales, France"}]},{"given":"Guillaume","family":"Demoor","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, IMT Mines Ales, Ales, France"}]},{"given":"Simon","family":"Chalm\u00e9","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, IMT Mines Ales, Ales, France"}]},{"given":"Nicolas","family":"Sutton-Charani","sequence":"additional","affiliation":[{"name":"EuroMov Digital Health in Motion, Univ Montpellier, IMT Mines Ales, Ales, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3458-0552","authenticated-orcid":false,"given":"Baptiste","family":"Magnier","sequence":"additional","affiliation":[{"name":"EuroMov Digital Health in Motion, Univ Montpellier, IMT Mines Ales, Ales, France"},{"name":"Service de M\u00e9decine Nucl\u00e9aire, Centre Hospitalier Universitaire de N\u00eemes, Universit\u00e9 de Montpellier, N\u00eemes, France"}]}],"member":"1968","published-online":{"date-parts":[[2024,10,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/j.neunet.2012.02.016","article-title":"Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition","volume":"32","author":"Stallkamp","year":"2012","journal-title":"Neural Netw."},{"key":"ref_2","unstructured":"Zaklouta, F., Stanciulescu, B., and Hamdoun, O. (August, January 31). Traffic sign classification using K-d trees and Random Forests. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), San Jose, CA, USA."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Cire\u015fan, D., Meier, U., Masci, J., and Schmidhuber, J. (2012, January 16\u201321). Multi-Column Deep Neural Network for Traffic Sign Classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.","DOI":"10.1016\/j.neunet.2012.02.023"},{"key":"ref_4","unstructured":"Sermanet, P., and LeCun, Y. (August, January 31). Traffic sign recognition with multi-scale Convolutional Networks. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), San Jose, CA, USA."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Fu, M.-Y., and Huang, Y.-S. (2010, January 11\u201314). A survey of traffic sign recognition. Proceedings of the IEEE International Conference on Wavelet Analysis and Pattern Recognition, Qingdao, China.","DOI":"10.1109\/ICWAPR.2010.5576425"},{"key":"ref_6","unstructured":"Stallkamp, J., Schlipsing, M., Salmen, J., and Igel, C. (August, January 31). The German Traffic Sign Recognition Benchmark: A multi-class classification competition. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), San Jose, CA, USA."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1016\/j.jvcir.2005.10.003","article-title":"Recognition of traffic signs based on their colour and shape features extracted using human vision models","volume":"17","author":"Gao","year":"2006","journal-title":"J. Vis. Commun. Image Represent."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Bahlmann, C., Zhu, Y., Ramesh, V., Pellkofer, M., and Koehler, T. (2005, January 6\u20138). A system for traffic sign detection, tracking, and recognition using color, shape, and motion information. Proceedings of the IEEE Proceedings. Intelligent Vehicles Symposium, Las Vegas, NV, USA.","DOI":"10.1109\/IVS.2005.1505111"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Broggi, A., Cerri, P., Medici, P., Porta, P.P., and Ghisio, G. (2007, January 13\u201315). Real Time Road Signs Recognition. Proceedings of the IEEE Proceedings. Intelligent Vehicles Symposium, Istanbul, Turkey.","DOI":"10.1109\/IVS.2007.4290244"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1038\/nbt1206-1565","article-title":"What is a support vector machine?","volume":"24","author":"Noble","year":"2006","journal-title":"Nat. Biotechnol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Izenman, A.J. (2013). Linear Discriminant Analysis. Modern Multivariate Statistical Techniques, Springer.","DOI":"10.1007\/978-0-387-78189-1_8"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi","year":"2021","journal-title":"J. Big Data"},{"key":"ref_14","unstructured":"Dalal, N., and Triggs, B. (2005, January 20\u201325). Histograms of oriented gradients for human detection. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), San Diego, CA, USA."},{"key":"ref_15","unstructured":"Alibrahim, H., and Ludwig, S.A. (July, January 28). Hyperparameter Optimization: Comparing Genetic Algorithm against Grid Search and Bayesian Optimization. Proceedings of the IEEE Congress on Evolutionary Computation (CEC), Krak\u00f3w, Poland."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","article-title":"Taking the Human out of the Loop: A Review of Bayesian Optimization","volume":"8","author":"Shahriari","year":"2016","journal-title":"Proc. IEEE"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bousquet, O., von Luxburg, U., and R\u00e4tsch, G. (2003). Gaussian Processes in Machine Learning. Advanced Lectures on Machine Learning, Springer.","DOI":"10.1007\/b100712"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4771","DOI":"10.1007\/s10462-021-10011-5","article-title":"How to tune the RBF SVM hyperparameters? An empirical evaluation of 18 search algorithms","volume":"54","author":"Wainer","year":"2021","journal-title":"Artif. Intell. Rev."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Azzopardi, L., Stein, B., Fuhr, N., Mayr, P., Hauff, C., and Hiemstra, D. (2019). Impact of Training Dataset Size on Neural Answer Selection Models. Advances in Information Retrieval, Springer.","DOI":"10.1007\/978-3-030-15719-7"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/10\/621\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:10:37Z","timestamp":1760112637000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/10\/621"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,10]]},"references-count":19,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["info15100621"],"URL":"https:\/\/doi.org\/10.3390\/info15100621","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,10]]}}}