Turkish Traffic Sign Recognition: Comparison of Training Step Numbers and Lighting Conditions

Abstract

With the ever increasing number of vehicles on the roads, traffic signs are becoming more and more important every passing day. Despite the fact that traffic signs are simple and easy to understand, in congested traffic drivers may miss them. Considering that even milliseconds can make a huge difference in preventing accidents, it would make a big help if a system could assist the driver with traffic signs. In order to achieve this, a traffic sign recognition system needs to be implemented. Accordingly, this study aims to develop a Turkish traffic sign detection and recognition system using the Faster R-CNN algorithm. The proposed solution utilizes TensorFlow framework and specifically makes use of the Faster R-CNN Inception-v2-COCO to train the object detection model. For training purposes, indigenous dataset is created containing 54 classes and 10842 Turkish traffic sign images. The training process of the model is carried out twice with step numbers 51,217 and 200,000, respectively. Then, these two models are used to detect 10 Turkish traffic sign images taken both daytime and nighttime. The results indicate that the proposed system’s average precision is 67.2% and average recall is 78.3% when trained with 51,217 steps; on the other hand, the average precision increases to 76% and average recall to 82.8% when trained with 200,000 steps.