【摘要】 要提高手写字符的识别率,关键在于提高相似字符的识别率。主曲线是一种新的基于非线性变换的特征抽取方法,它是通过数据分布"中间"并满足"自相合"的光滑曲线,较好地反映了数据分布的结构特征。本文尝试用主曲线这种新的方法来提取手写字符的结构特征,并基于这些特征来对相似字符进行模糊分类。所提方法在CE-DAR和OCRD手写体字符数据库上的实验结果表明:该方法不但是可行的,而且能有效提高相似字符的识别率,它为字符识别的研究提供了一条新途径。更多还原

【Abstract】 Effective differentiation of similar characters is critical to improving the recognition rate of off-line handwritten characters. Principal curves are a new feature extraction method based on nonlinear transformation. They are smooth self-consistent curves that pass through the "middle" of the distribution. They preferably reflect the structural features of the data. The paper chooses principal curves to extract structural features of characters. Fuzzy classification for similar characters based on these features is carried out. The CEDAR and OCRD handwritten character databases are used in the experiment. The experimental result shows that the proposed method can effectively improve the recognition rate of similar characters and provide a new approach to the research for character recognition.更多还原