본문 바로가기
  • Home

Seal Detection in Scanned Documents

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2013, 18(12), pp.65-73
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

Kyeonah Yu 1 김경혜 1

1덕성여자대학교

Accredited

ABSTRACT

As the advent of the digital age, documents are often scanned to be archived or to be transmitted over the network. The largest proportion of documents is texts and the next is seal images indicating the author of the documents. While a lot of research has been conducted to recognize texts in scanned documents and commercialized text recognizing products are developed as highlighted the importance of the scanned document, information about seal images is discarded. In this paper, we study how to extract the seal image area from the color or black and white document containing the seal image and how to save the seal image. We propose a preprocessing step to remove other components except for the candidate outlines of the seal imprint from scanned documents and a method to select the final region of interest from these candidates by using the feature of seal images. Also in case of a seal imprint overlapped with texts, the most similar image among those stored in the database is selected through the template matching process. We verify the implemented system for a various type of documents produced in schools and analyze the results.

Citation status

* References for papers published after 2022 are currently being built.