Recognition and detection with deep learning methods
Authors: Eskicioğlu Ömer Can, Dolićanin Edin, Işık Ali Hakan, Rifai Kuçi
Keywords: image preprocessing; VGG-16; Xception; CLAHE method; traffic sign detection
Abstract:
The method of recognizing traffic signs through image processing has increased in popularity along with advanced driver assistance systems. Drivers may have difficulty reading and detecting traffic signs due to fatigue, weather conditions and speed while driving. In our study, traffic signs rectangular, square, circle and so on. Regardless of the type of different plates seen in the country, even if the correct detection is aimed. By sending the model as a parameter while training, the only thing that needs to be done within the scope of adding a new plate is to retrain our model. Before starting learning, the image was enhanced to improve the performance of the algorithm by using the Contrast Restricted Adaptive Histogram Equation (CLAHE) method in data processing. In our study, results were obtained with 2 deep learning models unlike classical CNN architecture. VGG-16 and Xception deep learning models were compared with each other. SGD and Adam optimization methods were tried for both models and the optimum method was found for our study. Our study has reached an accuracy value of up to 98.38%. The speed performance of our method is sufficient to enable a real-time system implementation in the future. In order to understand the results of our experimental tests in the system to be used, it has been turned into a return parameter and the driver can be integrated with the vehicle regardless of the screen and used with voice assistant or small structures to be added independently of the vehicle.
References:
[1] BURÇIN, K.U.R.T., NABIYEV, V.V. (2010) Dijital Mamografi Görüntülerinin Kontrast Sınırlı Adaptif Histogram Esitleme ile Iyilestirilmesi. u: Proceedings of the VII. Ulusal Tıp Bilisimiimi Kongresi, Gazimagusa, KKTC, 14-17
[2] DEMIR, E. (2011) Trafik Levhası Belirleme ve Tanımlanması. http://doczz.biz.tr/doc/277231/itrafik-levhası-belirleme-ve-tanımlanması-ersin
[3] DOGAN, F., TURKOGLU, I. (2018) Derin Ogrenme Algoritmalarının Yaprak Sınıflandırma Basarımlarının Karsılastırılmasi. Sakarya University Journal of Computer and Information Sciences, 1(1): 10-21
[4] ETYEMEZ, A., MUSTAFA, K.U.R.T. Yapay Sinir Agları Yöntemiile Optimum Takım Seçimi. El-Cezeri Journal of Science and Engineering, 6(2): 323-332
[5] GULCU, A., KUS, Z. (2019) Konvolüsyonel Sinir Aglarında Hiper-Parametre Optimizasyonu Yöntemlerinin. Incelenmesi, Gazï Universitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji,
[6] GUNDUZ, H., KAPLAN, S., GUNAL, S., AKINLAR, C. (2013) Circular traffic sign recognition empowered by circle detection algorithm. u: 2013 21st Signal Processing and Communications Applications Conference (SIU). IEEE, pp. 1-4
[7] HIJAZI, S.L., KUMAR, R., ROWEN, C. (2015) Using Convolutional Neural Networks for Image Recognition, Erisim Tarihi: 15.06.2019. https://www.semantic scholar.org/paper/Using-Convolutional-Neural-Netwo rks-for-Image-By-Hijazi-Kumar/bbf7b5bdc39f9b8849c639c11f4726e3
[8] KARADAG, M., VURAL, U.C., KARASU, B. Otomotiv Sektöründe Cam. El-Cezeri Journal of Science and Engineering, 6(2): 299-322
[9] KIM, Y., TEASUP, M. (2016) Human Detection and Activity Classification Based on Micro-Doppler Signatures Using Deep Convolutional Neural Networks. IEEE Geoscience and Remote Sensing Letters, 13(1): 8-12
[10] KORU, M.T., AKGUNGOR, A.P., KORKMAZ, E. (2017) Trafik Tıkanıklıgının Fiyatlandırılması ve Uygulamalarının Incelenmesi: Kızılay Ankarä Ornegi. El-Cezeri Journal of Science and Engineering, 4(3): 497-508
[11] LEE, H., GROSSE, R., RANGANATH, R., NG, A.Y. (2009) Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. u: Proceedings of the 26th annual international conference on machine learning, ACM
[12] NECATI, A.K.S.U., KENAN, U.C.A.N. (2016) Zaman ve Konum Girdileri Kullanılarak Yapay Sinir Aglarıyla Referans Evapotranspirasyonun Tahmin Edilmesi. El-Cezeri Journal of Science and Engineering, 3(2)
[13] ONAT, E., UZDIL, U. (2015) Traffic sign classification using hough transform and SVM. u: 2015 23nd Signal Processing and Communications Applications Conference (SIU), IEEE, 2161-2165
[14] OZKAN, I.N.I.K., ULKER, E. Derin Ogrenme ve Goruntu Analizinde Kullanılan Derin Ogrenme Modelleri. Gaziosmanpasa Bilimsel Arastırma Dergisi, 6(3): 85-104
[15] SERENGIL, S.I. (2017) A Gentle Introduction to Convolutional Neural Networks, Erisim Tarihi: 10.06.2019. https://sefiks.com/2017/11/03/a-gentle-introduction-to-convolutionalneural-networks
[16] SRIVASTAVA, N., HINTON, G.E., KRIZHEVSKY, A., SUTSKEVER, I., SALAKHUTDINOV, R. (2014) Dropout: A simple way to prevent neural networks from overfitting. Journal of machine learning research, 15(1): 1929-1958
[17] SURUCU, E.A., DOGAN, H. (2018) Traffic sign recognition with hierarchical Convolutional Neural Network. u: 2018 26th Signal Processing and Communications Applications Conference (SIU) IEEE, pp. 1-4
[18] TEO, C.K. (2003) Digital Enhancement of Night Vision and Thermal Images. California: Naval Postgraduate School, Thesis
[19] TURKOGLU, M., HANBAY, D. (2018) Apricot disease identification based on attributes obtained from deep learning algorithms. u: 2018 International Conference on Artificial Intelligence and Data Processing (IDAP) IEEE, pp. 1-4
[20] YALÇIN, H., IRMAK, H., BULUT, M.M., AKAR, G.B. (2013) Real-time Traffic Sign detection and Recognition on FPGA. u: 2013 21st Signal Processing and Communications Applications Conference (SIU), IEEE, pp. 1-4
[21] YOON, H., HAN, Y., HAHN, H. (2009) Image Contrast Enhancement based Sub-histogram Equalization Technique without Over-equalization Noise. International Journal of Computer Science and Engineering, 3
[22] Convolutional Neural Network (Evris¸imsel Sinir Agları), https://medium.com/@rabiaokumus96/convolutional-neural-networks-evris¸imsel-siniragları-cceb887a2979. ˘
[23] Image Recognition using Pre Trained Xception Model in 5 steps, https://medium.com/@gkadusumilli/image-recognition-using-pre-trained-xception-modelin-5-steps-96ac858f4206. 2019.
[24] WILDML. Understandıng Convolutional Neural Networks For NLP, http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp/. 2016.