Segmentation of text, picture and lines of a document image

Image analysis – Histogram processing – For setting a threshold

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

382 46, 382 56, 3582611, G06K 934

Patent

active

053352904

ABSTRACT:
In a character recognition system, a method and apparatus for segmenting a document image into areas containing text and non-text. Document segmentation in the present invention is comprised generally of the steps of: providing a bit-mapped representation of the document image, extracting run lengths for each scanline from the bit-mapped representation of the document image; constructing rectangles from the run lengths; initially classifying each of the rectangles as either text or non-text; correcting for the skew in the rectangles; merging associated text into one or more text blocks; and logically ordering the text blocks.

REFERENCES:
patent: 4411015 (1983-10-01), Scherl et al.
patent: 4503556 (1985-03-01), Scherl et al.
patent: 4776024 (1988-10-01), Katoh et al.
patent: 4817169 (1989-03-01), Peppers et al.
patent: 4866784 (1989-09-01), Barski
patent: 5191438 (1993-03-01), Katsurada
S. Tsujimoto and H. Asada, "Understanding Multi-articled Documents," Research and Development Center, Toshiba Corporation, IEEE, pp. 551-556 (Jun. 1990).
F. Esposito, D. Malerba, G. Semeraro, E. Annese, and G. Scafuro, "Empirical Learning Methods For Digitized Document Recognition: An Integrated Approach to Inductive Generalization," University of Bari, Olivetti Systems & Networks, pp. 37-45 (Jun. 1990).
A. Dengel & G. Barth, "ANASTASIL: A Hybrid Knowledge-based System for Document Layout Analysis," German Research Center for Artificial Intelligence (DFKI), Knowledge Representation, pp. 1249-1254 (Aug. 1989).
M. Yamada, K. Hasuike, "Document Image Processing Based on Enhanced Border Following Algorithm," Research and Development Laboratories, IEEE, pp. 231-236 (Jun. 1990).
J. Higashino, H. Fujisawa, Y. Nakano, and M. Ejiri, "A Knowledge-based Segmentation Method for Document Understanding," Central Research Laboratory, Hitachi, Ltd., IEEE, pp. 744-748 (Oct. 27-31 1986).
L. A. Fletcher and R. Katsuri, "A Robust Algorithm for Test String Separation from Mixed Text/Graphics Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, No. 6, pp. 910-918 (Nov. 1988).
F. M. Wahl, K. Y. Wong, and R. G. Casey, "Block Segmentation and Text Extraction in Mixed Test/Image Documents," IBM Research Laboratory, Computer Graphics and Image Processing, pp. 375-390 (1982).
F. M. Wahl and K. Y. Wong, "Efficient Method for Running a Constrained Run Length Algorithm in Vertical and Horizontal Direction on Binary Image Data," IBM Technical Disclosure Bulletin, vol. 25, No. 6, pp. 2881-2883 (Nov. 1982).
H. S. Baird, S. E. Jones, and S. J. Fortune, "Image Segmentation by Shape-Directed Covers," AT&T Bell Laboratories, IEEE, pp. 820-825 (Jun. 1990).
T. Pavlidis, "A Vectorizer and Feature Extractor for Document Recognition," AT&T Bell Laboratories, Computer, Vision, Graphics, and Image Processing, vol. 35, pp. 111-127 (1986).
H. S. Baird, "Global-to-Local Analysis," AT&T Bell Laboratories, pp. 1-16 (Sep. 1988).
S. N. Srihari and V. Govindaraju, "Analysis of Textual Images Using the Hough Transform," Department of Computer Science, Machine Vision and Applications, pp. 141-153 (1989).

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Segmentation of text, picture and lines of a document image does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Segmentation of text, picture and lines of a document image, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Segmentation of text, picture and lines of a document image will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-70519

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.