Tablet inscription recognition based on the convolutional neural network

Abstract

Text image recognition has opened up a new path for intelligent text sorting and research. The number of epitaph inscriptions is very large and of great value. Due to the limitation of objective conditions, there are many deficiencies in the study of its text arrangement and it is urgent to adopt new methods and new technologies to overcome them. This paper attaches great importance to the design of an automatic recognition algorithm for tablets based on the convolutional neural network. It also describes the application prospects of using the algorithm for the reading and distinguishing of inscriptions, the sorting of inscriptions, and the building of intelligent databases.