Research on the Construction of the Basic Database of Uygur Online Handwriting

Uygur language is one of the official languages in Xinjiang Uygur Autonomous Region. At present, the development of its handwriting technology is still lagging behind, and its text input is still stuck in the stage of keyboard encoding. Based on English, Arabic and other handwriting recognition technologies, and combined with the structure, word formation features, input habit and other characteristics of Uygur language, this paper studies the establishment of a large-scale sample basic database of Uygur online handwriting, discusses the collection of samples and the organization form of data, and analyzes the effect of the number of training samples on the performance of recognition by experiment.