Food object recognition and intelligent billing system based on Cascade R-CNN

摘要

With the development of information technology and artificial intelligence, using science and technology to change the low efficiency of the catering industry is a very effective means. The existing system of food identification and intelligent billing in the market includes artificial billing, RFID induction, photo recognition, etc. Based on the Cascade R-CNN algorithm and computer vision technology, this paper proposes an intelligent food identification and intelligent billing system. First, the database is created for algorithm training, then the mobile device is used to collect the food image, and the depth neural network is used to identify the food in the image. Finally, the price calculation result of each is found and returned to the user. In this paper, the basic principle and implementation method of the system are described in detail, and the experimental phenomenon is analyzed. The experimental results show that the system has good accuracy.