THE DOCUMENT SPECTRUM FOR PAGE LAYOUT ANALYSIS

被引:357
作者
OGORMAN, L
机构
[1] AT&T Bell Laboratories, Murray Hill, NJ.
关键词
DOCUMENT IMAGE PROCESSING; GEOMETRIC PAGE LAYOUT ANALYSIS; PAGE SEGMENTATION; SKEW ESTIMATION; STRUCTURAL PAGE LAYOUT ANALYSIS;
D O I
10.1109/34.244677
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Page layout analysis is a document processing technique used to determine the format of a page. This paper describes the document spectrum, or docstrum, which is a method for structural page layout analysis based on bottom-up, nearest-neighbor clustering of page components. The method yields an accurate measure of skew, within-line, and between-line spacings and locates text lines and text blocks. It is advantageous over many other methods in three main ways: independence from skew angle, independence from different text spacings, and the ability to process local regions of different text orientations within the same image. Results of the method shown for several different page formats and for randomly oriented subpages on the same image illustrate the versatility of the method. We also discuss the differences, advantages, and disadvantages of the docstrum with respect to other lay-out methods.
引用
收藏
页码:1162 / 1173
页数:12
相关论文
共 20 条
  • [1] AUTOMATED ENTRY SYSTEM FOR PRINTED DOCUMENTS
    AKIYAMA, T
    HAGITA, N
    [J]. PATTERN RECOGNITION, 1990, 23 (11) : 1141 - 1154
  • [2] BAIRD HS, 1990, 10TH P INT C PATT RE, P820
  • [3] BAIRD HS, 1987, MAY P C SOC PHOT SCI, P14
  • [4] Duda R., 1973, PATTERN CLASSIFICATI, P103
  • [5] ESPOSITO R, 1990, 10TH P INT C PATT RE, P557
  • [6] FISHER JL, 1990, 10TH P INT C PATT RE, P567
  • [7] A METHOD OF DETECTING THE ORIENTATION OF ALIGNED COMPONENTS
    HASHIZUME, A
    YEH, PS
    ROSENFELD, A
    [J]. PATTERN RECOGNITION LETTERS, 1986, 4 (02) : 125 - 132
  • [8] HINDS S, 1990, 10TH P INT C PATT RE, P464
  • [9] AN OBJECT MODEL FOR IMAGE RECOGNITION
    JAGADISH, HV
    OGORMAN, L
    [J]. COMPUTER, 1989, 22 (12) : 33 - 41
  • [10] Nagy G., 1984, Seventh International Conference on Pattern Recognition (Cat. No. 84CH2046-1), P347