Character segmentation and retrieval for learning support system of Japanese historical books
Chulapong Panichkriangkrai, Liang Li, Kozaburo Hachimura · 2013
This paper proposes a character segmentation and retrieval method for a learning support system that analyzes digitized Japanese historical woodblock printed books. The proposed system detects text lines, segments characters, and retrieves similar characters from document images. The process includes background separation, text line extraction, rule-based character integration and segmentation, and similar character retrieval. The experimental results show that the proposed method segmented all text lines correctly and successfully extracted more than 79% of the complicated characters, as well as provided promising character retrieval results.