作者: Satoshi Naoi , Yoshinobu Hotta , Jun Sun , Hao Yu
DOI:
关键词:
摘要: A method for processing a document image includes: performing horizontal and vertical text line extraction on the image; providing an overlapping matrix, value of element matrix indicating relation between lines; merging in direction; determining one or more regions image, based values elements merged matrix; counting total number strokes pixel points lines, respectively, within regions; orientation region is if lines larger than that otherwise, vertical.