At present, research work on pedestrian detection, forward collision avoidance and other applications emerges in an endless stream, but there is not much work on road signal detection and recognition. As a public facility that provides drivers with basic road information, the importance of traffic signs is unquestionable. The purpose of this paper is to study road sign recognition techniques incorporating deep learning. A method that combines traditional image processing is proposed. After the redundant elements in the dataset images are removed and learned by the network model, the network model combining the residual network concept and SENet concept is compared in day and night scenes, and the recognition accuracy proves the effectiveness of the proposed algorithm . The trained road sign recognition network is used to complete offline video road sign recognition experiments at all levels, and the experimental results are analyzed. In the daytime scene, a recall rate of 0.96 and a precision rate of 0.98 were obtained. In the night scene, a recall rate of 0.89 and a precision rate of 0.91 were obtained.

Varun Kavita. Road Sign Recognition Technology Integrating Deep Learning. International Journal of Neural Network (2020), Vol. 1, Issue 2: 32-39. https://doi.org/10.38007/NN.2020.010205.

[1] Faiedh H, Hamdi S, Bouguezzi S, et al. Architectural exploration of multilayer perceptron models for on-chip and real-time road sign classification:. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, 2018, 232(6):772-783. https://doi.org/10.1177/0959651818778478

[2] Akshay G, Dinesh K, Nagaraj. Road sign recognition system using raspberry PI. International Journal of Pure and Applied Mathematics, 2018, 119(15):1845-1850.

[3] Hasegawa R, Iwamoto Y, Chen Y W. Robust Japanese Road Sign Detection and Recognition in Complex Scenes Using Convolutional Neural Networks. Journal of Image and Graphics, 2020, 8(3):59-66. https://doi.org/10.18178/joig.8.3.59-66

[4] Al-Shamayleh A S, Ahmad R, Jomhari N, et al. Automatic Arabic Sign Language Recognition: A Review, Taxonomy, Open Challenges, Research Roadmap And Future Directions. Malaysian Journal of Computer Science, 2020, 33(4):306-343. https://doi.org/10.22452/mjcs.vol33no4.5

[5] BA Akgül, Haznedar B, Hasoglu M F, et al. Development of a Real-Time Traffic Sign Recognition System Based On Deep Learning Approach with Convolutional Neural Networks and Integrating to The Embedded Systems. Euroasia Journal of Mathematics Engineering Natural and Medical Sciences, 2020, 8(14):46-64.

[6] Kumar K A, Gowtham S, Kumar M M, et al. Automatic recognition of sign-boards using myRIO. International Journal of Pure and Applied Mathematics, 2018, 119(12):14555-14562.

[7] Hasegawa R, Iwamoto Y, Chen Y W. Robust Japanese Road Sign Detection and Recognition in Complex Scenes Using Convolutional Neural Networks. Journal of Image and Graphics, 2020, 8(3):59-66. https://doi.org/10.18178/joig.8.3.59-66

[8] Khayeat A, Abdulmunem A A, Al-Shammari R, et al. Traffic Sign Detection and Classification based on Combination of MSER Features and Multi-language OCR. Webology, 2020, 17(2):394-403. https://doi.org/10.14704/WEB/V17I2/WEB17040

[9] Kamruzzaman M M. Arabic Sign Language Recognition and Generating Arabic Speech Using Convolutional Neural Network. Wireless Communications and Mobile Computing, 2020, 2020(6):1-9. https://doi.org/10.1155/2020/3685614

[10] Kim H G, Jeong H, Lim H T, et al. Binocular Fusion Net: Deep Learning Visual Comfort Assessment for Stereoscopic 3D. IEEE Transactions on Circuits and Systems for Video Technology, 2019, 29(4):956-967. https://doi.org/10.1109/TCSVT.2018.2817250

[11] Lavinia Y, Vo H, Verma A. New colour fusion deep learning model for large-scale action recognition. International journal of computational vision and robotics, 2020, 10(1):41-60. https://doi.org/10.1504/IJCVR.2020.104356

[12] Siddiqui S Y, Naseer I, Khan M A, et al. Intelligent Breast Cancer Prediction Empowered with Fusion and Deep Learning. Cmc -Tech Science Press-, 2020, 67(1):1033-1049. https://doi.org/10.32604/cmc.2020.013952

[13] Abdi A, Shamsuddin S M, Hasan S, et al. Deep learning-based sentiment classification of evaluative text based on Multi-feature fusion. Information Processing & Management, 2019, 56(4):1245-1259. https://doi.org/10.1016/j.ipm.2019.02.018

[14] Khayyat M M, Elrefaei L A. Manuscripts Image Retrieval Using Deep Learning Incorporating a Variety of Fusion Levels. IEEE Access, 2020, PP(99):1-1. https://doi.org/10.1109/ACCESS.2020.3010882

[15] Saba T, Mohamed A S, El-Affendi M, et al. Brain tumor detection using fusion of hand crafted and deep learning features. Cognitive Systems Research, 2020, 59(Jan.):221-230. https://doi.org/10.1016/j.cogsys.2019.09.007

[16] Wekesa J, Meng J, Luan Y. Multi-feature fusion for deep learning to predict plant lncRNA-protein interaction. Genomics, 2020, 112(5):2928-2936. https://doi.org/10.1016/j.ygeno.2020.05.005 

[17] Usama M, Xiao W, Ahmad B, et al. Deep Learning based Weighted Feature Fusion Approach for Sentiment Analysis. IEEE Access, 2019, 7(99):140252-140260. https://doi.org/10.1109/ACCESS.2019.2940051

[18] Lahaye N, Ott J, Garay M J, et al. Multi-Modal Object Tracking and Image Fusion with Unsupervised Deep Learning. Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of, 2019, 12(8):3056-3066. https://doi.org/10.1109/JSTARS.2019.2920234