Page segmentation for document image analysis using a neural network

被引:9
作者
Patel, D [1 ]
机构
[1] UNIV LONDON, ROYAL HOLLOWAY & BEDFORD NEW COLL, DEPT PHYS, EGHAM TW20 0EX, SURREY, ENGLAND
关键词
document page segmentation; texture analysis; artificial neural networks; convolution; entropy thresholding;
D O I
10.1117/1.600618
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
In this paper we present a method for segmenting document page images into text and nontext regions. The underlying assumption made by this approach is that the two regions can be viewed as different textures. We do not use any a priori knowledge of the document format. A convolution-based method is used to generate the texture feature images. The coefficients of the convolution masks are obtained using a single-layer artificial neural network that generates eigenvectors of the correlation matrix of the input data. The coefficients of these masks have been ''learned'' from examples of the document images and have a potential of being considerably more powerful than masks with preset coefficients. A thresholding scheme based on a measure of entropy is used to Segment the feature images into the homogeneous regions. (C) 1996 Society of Photo-Optical instrumentation Engineers.
引用
收藏
页码:1854 / 1861
页数:8
相关论文
共 38 条
[1]   AUTOMATIC THRESHOLDING OF GRAY-LEVEL PICTURES USING TWO-DIMENSIONAL ENTROPY [J].
ABUTALEB, AS .
COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1989, 47 (01) :22-32
[2]   CHARACTERIZATION OF TEXTURES BY EIGENFILTERS [J].
ADE, F .
SIGNAL PROCESSING, 1983, 5 (05) :451-457
[3]  
[Anonymous], 1970, PICTURE PROCESSING P
[4]   UNCERTAINTY RELATION FOR RESOLUTION IN SPACE, SPATIAL-FREQUENCY, AND ORIENTATION OPTIMIZED BY TWO-DIMENSIONAL VISUAL CORTICAL FILTERS [J].
DAUGMAN, JG .
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1985, 2 (07) :1160-1169
[5]   HIGH CONFIDENCE VISUAL RECOGNITION OF PERSONS BY A TEST OF STATISTICAL INDEPENDENCE [J].
DAUGMAN, JG .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1993, 15 (11) :1148-1161
[6]  
Davies E. R., 1995, Real-Time Imaging, V1, P397, DOI 10.1006/rtim.1995.1041
[7]   TEXTURE FEATURE PERFORMANCE FOR IMAGE SEGMENTATION [J].
DUBUF, JMH ;
KARDAN, M ;
SPANN, M .
PATTERN RECOGNITION, 1990, 23 (3-4) :291-309
[8]  
DUDA R. O., 2000, Pattern Classification and Scene Analysis
[9]  
DUNN DF, 1992, P SOC PHOTO-OPT INS, V1826, P51, DOI 10.1117/12.131586
[10]  
ETEMAD K, 1995, CSTR3444 U MAR