A Hangul Document Image Retrieval System Using Rank-based Recognition

웨이브렛 특징과 순위 기반 인식을 이용한 한글 문서 영상 검색 시스템

  • 이득용 (전북대학교 컴퓨터과학과) ;
  • 김우연 (전북대학교 컴퓨터과학과) ;
  • 오일석 (전북대학교 컴퓨터과학과)
  • Published : 2005.04.01


We constructed a full-text retrieval system for the scanned Hangul document images. The system consists of three parts; preprocessing, recognition, and retrieval components. The retrieval algorithm uses recognition results up to k-ranks. The algorithm is not only insensitive to the recognition errors, but also has the advantage of user-controllable recall and precision. For the objective performance evaluation, we used the scanned images of the Journal of Korea Information Science Society provided by KISTI. The system was shown to be practical through theevaluationofrecognitionandretrievalrates.


Document Image;Full-Text Retrieval;OCR;Recall and Precision