Traffic Sign Recognition Method Based on Simplified Gabor Wavelets and CNNs
Mukhriddin UmarovTashkent University of Information Technologies named after Al-Kharezmi, Tashkent, UzbekistanFarrukh MuradovTashkent University of Information Technologies named after Al-Kharezmi, Tashkent, UzbekistanTemur Azamovdept. The Ministry of Information Technologies and Communications of the Republic of Uzbekistan,Tashkent,Uzbekistan
2021 International Conference on Information Science and Communications Technologies (ICISCT)conference2021en
ABI
Abstract
Nowadays, as the number of cars increases, it is important to solve the problem of The automatic traffic sign detection and recognition (TSDR). We aimed to identify road signs from the images that provide information about the road infrastructure. A simplified Gabor wavelet filter provides good efficiency in identifying an important feature of traffic signs. convolutional neural networks (CNNs) is most commonly used in recognizing objects from images. In our approach, the simplified Gabor wavelet filter and CNN detection of traffic signs gave good results.