Semantic-Based Handwritten Chinese Character Recognition Model

There have been many different literals discussing algorithms for handwritten Chinese character recognition, but most algorithms aim at recognizing isolated Chinese character one by one. Therefore, their recognition accuracy isn´t good enough for the confusing characters. To solve this problem, this paper presents a new model, which considers the contextual semantics by means of Chinese dictionary based on isolated Chinese character recognition. The recognition accuracy for the confusing Chinese characters has been greatly improved with the new model.