텍스트-배경무늬 혼합문서로부터 수리형태학을 이용한 문자열 추출

String extraction from text-background mixed documents using mathematical morphology

It is known as a difficult problem to recognize text-background mixed documents. In this paper a new string extraction algorithm, using mathematical morphology for the document consisting of text and overlapped periodic background pattern, is proposed. The algorithm consists of pattern periodicity feature extraction and background removal. The extracted pattern periodicity feature is used to determine the shape of structuring elements for morphological pre- and post-processing to remove background. The effectiveness of the proposed algorithm over the existing one is also verified through the experiments with various test documents.