SEGMENTATION OF TOUCHING CHARACTERS IN PRINTED DOCUMENT RECOGNITION

[摘要] A new discrimination function is presented for segmenting touching characters based on both pixel and profile projections. A dynamic recursive segmentation algorithm is developed for effectively segmenting touching characters. Contextual information and spell checking are used to correct errors caused by incorrect recognition and segmentation. Based on 12 real documents, a maximum 99.85% and a minimum 99.4% recognition accuracy is achieved.

[发布日期] 1994-06-01

[关键词] TOUCHING CHARACTER SEGMENTATION;DYNAMIC RECURSIVE SEGMENTATION;CHARACTER CONTEXTUAL CLASSES;FEATURE EXTRACTION;SPELLING CORRECTION