| Popis: |
It is one of the ascendant research topics to study ancient literature by means of digital humanities technology, to construct the historical scene of literature, to restore the writer’s creative prosperity and to excavate the era value of ancient books. The digital reconstruction of ancient books has greatly impacted the preservation and inheritance of ancient literary resources. As an important carrier of ancient literature, ancient books have many texts that need to be identified, and it isn’t easy to disseminate in the information age due to their text form. This paper uses computer image processing methods to handle broken ancient text and obtain a more clearly visible digital form. At the same time, a method for document correction based on neural networks is proposed for certain texts that have occlusions and distortions. In several sets of experiments, it is shown that the document correction F1 value of the model in this paper is significantly ahead of the mainstream model with 0.903. Applying the digital platform for ancient books to the member groups of the Association for the Study of Ancient Literature, 81.5% of the respondents strongly agree with Q7, “I think the digital platform for ancient books is very conducive to cultural inheritance”, and the total of disagreeing and strongly disagreeing only accounts for 5%. It can be assumed that the ancient books digital platform designed in this paper and its document correction and recognition function have been widely recognized, and the ancient books digital platform can be applied to the digitization of ancient literature documents, daily reading, and storage of texts, text recognition, etc., contributing to the automation of ancient literature research, book storage and dissemination, and electronic reading. Based on this, the future database of ancient books should not only be a query and retrieval tool but also help scholars to make multidimensional statistics, comparisons, and analyses so as to generate new knowledge and ideas. |
