作者: Takashi Saitoh
DOI:
关键词:
摘要: An extracting step extracts text regions from an input document image. A classifying classifies the into in-order reading to be successively read in predetermined order and different-attribute regions. detecting detects construction of determining determines order, which are read, using construction. The a manner that is same whether image comprises vertically typeset or horizontally document. further includes tree graph formation c-1) forming representing including nodes respectively