作者: Hongxi Wei , Guanglai Gao
DOI: 10.1109/CISE.2009.5364627
关键词:
摘要: This paper presents a new method to recognize machine-printed traditional Mongolian characters by using back-propagation (BP) neural networks. First, the set of is divided into five subsets according each character's position (initial, medial or final) within word and some steady structural features. Then, subset trained recognized BP network with particular architecture. Thus, there are networks in total, which can all characters. The experimental results provided show that have good performance for recognition.