Material classification technology based on convolutional neural networks

The contact measurement techniques are typically used in the field of object material classification. It has a lot of disadvantages, such as the complex operation and time-consuming. In this paper, a new non-contact object material identification method based on Convolutional neural networks (CNNs) and polarization imaging is proposed. Firstly, the relationship between the complex refractive index of object and the polarization information is simulated, and then the structure of the CNNs is constructed according to the specific conditions of the polarization imaging system. The accuracy of the identification method is measured by repeated test using 7 materials. The experimental results show that the CNNs model can quickly realize the object material classification with the polarization images, and the classification accuracy is above 92%.