基于自适应特征与多级反馈模型中英文混排文档分割.pdfVIP

32 3  Vol. 32, No. 3 2006 5 ACTA AUTOMATICA SINICA May, 2006 1) Æ ( 100080) (E-mail: yong.xia@ia.ac.cn)  Æ Æ Æ Æ ℄ OCR TP391 Segmentation of Mixed Chinese/English Document Based on AFMPF Model XIA Yong WANG Chun-Heng DAI Ru-Wei (Institute of Automation, Chinese Academy of Sciences, Beijing 100080) (E-mail: yong.xia@ia.ac.cn) Abstract This paper proposes a novel method to segment document image based on adap- tive feature and multiple phase feedback (AFMPF) model, which is adaptive to the blurring of document image and various patterns of mixed Chinese/English document. First, the whole process of segmentation is divided into several phases and each phase is allocated a primary feature to segment document image. Second, the segmentation result of each phase is fed back to the current or previous phase, and directs the next phase segmenta- tion. This method causes good and effective combination among character segmentation, pre-classification of Chinese/English and character recognition, which improves greatly the accuracy of character segmentation and recognition. Key words Segmentation of mixed Chinese/English document, pre-classification of Chi- nese/English, adaptive feature and multiple phase feedback model (AFMPF model), adap- tation to various document image, OCR 1 [1∼3] , 1) Supported by National Natural Science Foundation of P.R. China