Fragmented-cuneiform-based convolutional neural network for cuneiform character recognition

Abstract

Cuneiform has been a widely used writing system in one of the human history phases. Although there are millions of tablets, have been excavated today, only around 100,000 tablets have been read. The difficulty in translating also increased if the tablet has damaged areas resulting in some of its characters become fragmented and hard to read. This paper investigates the possibility of reading fragmented cuneiform characters from Noto Sans Cuneiform font based on convolutional neural network (CNN). The dataset is built on extracted 921 characters from the font. These characters are then intentionally being damaged with specific patterns, resulting set of fragmented characters ready to be trained. The model produced by this training phase then being used to read the unseen fragmented pattern of cuneiform sets. The model also being tested for reading normal characters set. From the simulation, 83.86% accuracy of reading fragmented characters are obtained. Interestingly, 96.42% accuracy is obtained while the model is being tested for reading normal characters.