Blue-print document analysis for color classification

  • Gabriel Marcu
  • Satoshi Abe
Pattern Recognition and Document Processing

DOI: 10.1007/3-540-60298-4_316

Part of the Lecture Notes in Computer Science book series (LNCS, volume 974)
Cite this paper as:
Marcu G., Abe S. (1995) Blue-print document analysis for color classification. In: Braccini C., DeFloriani L., Vernazza G. (eds) Image Analysis and Processing. ICIAP 1995. Lecture Notes in Computer Science, vol 974. Springer, Berlin, Heidelberg

Abstract

The blue print copies result in common designing process by copying the half-transparent white paper hand drawn in black ink. Over the blue print papers, very often, the designer marks in different colors some area or symbols of interest. This paper presents the particularities of analysis of such kind of documents in order to extract the colored lines as well as the original blue lines resulted during the copying process. The procedure is based on processing for clusterization of the colormap of the original image, and on post processing of the resulted run-length files for each classified color. It runs for any size of the scanned image and is independent on the contents of the image. For A1 size document, the color classification and bynary coding takes 20 min for 400MB image data.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag 1995

Authors and Affiliations

  • Gabriel Marcu
    • 1
  • Satoshi Abe
    • 1
    • 2
  1. 1.Array CorporationTokyoJapan
  2. 2.Department of Information Science, Fac. of ScienceUniv. of TokyoJapan

Personalised recommendations