With the continuous development of intelligent transportation system. Traffic sign recognition system as a key part of it, its research and practice can bring more convenience to people's lives. In order to solve the problems in the research of traffic sign detection and recognition methods, based on the discussion of image preprocessing technology, target detection technology, target recognition technology and improved support vector machine algorithm principle in recognition, this paper briefly discusses the traffic sign area screening and actual data samples, and discusses the design of recognition model. Finally, the recognition model designed in this paper is compared with the cyclic neural network (CNN) and decision tree (DT) through experimental tests. The experimental results show that the improved support vector machine (ISVM) has an average recognition accuracy of 97.03% for red speed limit, blue, danger and speed limit removal. ISVM has better detection and recognition rate than cyclic neural network (CNN) and decision tree (DT). Therefore, the algorithm proposed in this paper has high practical value in traffic sign detection and recognition.

Sen Zhao and Tong Han. Traffic Sign Detection and Recognition Based on Color Features and Improved Support Vector Machine Algorithm. Machine Learning Theory and Practice (2021), Vol. 2, Issue 4: 10-17. https://doi.org/10.38007/ML.2021.020402.

[1] Farhat W, Sghaier S, Faiedh H, et al. Design of efficient embedded system for road sign recognition. Journal of ambient intelligence and humanized computing, 2019, 10(2):491-507. https://doi.org/10.1007/s12652-017-0673-3

[2] Ibrahim N B, Selim M M, Zayed H H. An Automatic Arabic Sign Language Recognition System (ArSLRS). Journal of King Saud University - Computer and Information Sciences, 2018, 30(4):470-477. https://doi.org/10.1016/j.jksuci.2017.09.007

[3] Taylor, Topper. Terry Lutz of Signicast Receives Industry Recognition. International Magazine of the Investment Casting Institute, 2018, 31(4):6-6.

[4] Savant R, Ajay A. Indian Sign Language Recognition System For Deaf And Dumb Using Image Processing And Fingerspelling: A Technical Review. National Journal of System and Information Technology, 2018, 11(1):23-34.

[5] Neiva, Davi, Hirafuji, et al. Gesture recognition: A review focusing on sign language in a mobile context. Expert Systems with Application, 2018, 103(Aug.):159-183. https://doi.org/10.1016/j.eswa.2018.01.051

[6] Zare A A, Zahiri S H. Recognition of a real-time signer-independent static Farsi sign language based on fourier coefficients amplitude. International Journal of Machine Learning & Cybernetics, 2018, 9(5):727-741. https://doi.org/10.1007/s13042-016-0602-3

[7] Mott M, Midgley K J, Holcomb P J, et al. Cross-modal translation priming and iconicity effects in deaf signers and hearing learners of American Sign Language. Bilingualism: Language and Cognition, 2020, 23(5):1032-1044. https://doi.org/10.1017/S1366728919000889

[8] Khan, Jameel, Ahmed, et al. Efficient coarser-to-fine holistic traffic sign detection for occlusion handling. IET Image Processing, 2018, 12(12):2229-2237. https://doi.org/10.1049/iet-ipr.2018.5424

[9] Rycroft-Malone J, Mitchell I, Saultry B, et al. Prioritising Responses of Nurses to deteriorating patient Observations (PRONTO): a pragmatic cluster randomised controlled trial evaluating the effectiveness of a facilitation intervention on recognition and response to clinical deterioration. BMJ Quality and Safety, 2021, 82(N):1387-92.

[10] Dhanpat J, Higginson A, Brooks K. Estimation of the Effect of Bio-Admixtures on Concrete Workability Using Linear Regression and Support Vector Machines. IFAC-PapersOnLine, 2021, 54(21):133-138. https://doi.org/10.1016/j.ifacol.2021.12.023

[11] Kahl M, Kroll A. Extending Regularized Least Squares Support Vector Machines for Order Selection of Dynamical Takagi-Sugeno Models. IFAC-PapersOnLine, 2020, 53( 2):1182-1187. https://doi.org/10.1016/j.ifacol.2020.12.1331

[12] Kantavat P, Kijsirikul B, Songsiri P, et al. Efficient Decision Trees for Multi-Class Support Vector Machines Using Entropy and Generalization Error Estimation. International Journal of Applied Mathematics & Computer Science, 2018, 28(4):705-717. https://doi.org/10.2478/amcs-2018-0054

[13] Mathew J, Pang C K, Luo M, et al. Classification of Imbalanced Data by Oversampling in Kernel Space of Support Vector Machines. Neural Networks and Learning Systems, IEEE Transactions on, 2018, 29(9):4065-4076. https://doi.org/10.1109/TNNLS.2017.2751612

[14] Kim, Sungdo, Mun, et al. Data depth based support vector machines for predicting corporate bankruptcy. Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies, 2018, 48(3):791-804. https://doi.org/10.1007/s10489-017-1011-3

[15] Mohsen, Farhang, Ali, et al. Automatic modulation recognition for DVB-S2 using pairwise support vector machines. International journal of autonomous and adaptive communications systems: IJAACS, 2018, 11(2):144-153. https://doi.org/10.1504/IJAACS.2018.092020

[16] Silvina, Niell, Florencia, et al. Beehives biomonitor pesticides in agroecosystems: Simple chemical and biological indicators evaluation using Support Vector Machines (SVM). Ecological indicators: Integrating, monitoring, assessment and management, 2018, 91(Aug.):149-154. https://doi.org/10.1016/j.ecolind.2018.03.028

[17] Hossain M Z, Gedeon T, Sankaranarayana R. Using Temporal Features of Observers' Physiological Measures to Distinguish Between Genuine and Fake Smiles. IEEE Transactions on Affective Computing, 2020, 11(1):163-173. https://doi.org/10.1109/TAFFC.2018.2878029

[18] Williams, Julie, C, et al. Soluble CD14, CD163, and CD27 biomarkers distinguish ART‐suppressed youth living with HIV from healthy controls. Journal of Leukocyte Biology: An Official Publication of the Reticuloendothelial Society, 2018, 103(4):671-680. https://doi.org/10.1002/JLB.3A0717-294RR