Machine recognition efficiency study of safety signs based on image degradation simulation

This study focuses on the influence of image degradation on machine recognition of safety signs. This paper attempts to classify and grade the image degradation of safety signs. By the means of simulation, this paper also tries to break the limit of real-time image recognition. In this paper, the image degradation of safety signs is classified into 12 types. Each type is simulated by different ways of picture processing. All the pictures are performed machine recognition by convolutional neural network, and the accuracy is recorded. The mechanism of image degradation affecting the recognition efficiency is studied, and an A/B test with real-time safety signs is conducted to evaluate the performance. The results show that the effect of pixel displacement on the recognition efficiency is generally lower than the effect of pixel replacement by calculation. The effect on the recognition efficiency is smaller with less pixel displacement and simpler calculation. Overlay and fusion make the recognition efficiency unstable. The recognition efficiency of real-time safety signs will be higher when the test group contains degraded images as samples. The main part of a safety sign is very important in the recognition process and should be dealt with appropriate protection.