首页> 外文期刊>Optical Engineering >Extracting halftones from printed documents using texture analysis
【24h】

Extracting halftones from printed documents using texture analysis

机译:Extracting halftones from printed documents using texture analysis

获取原文
获取原文并翻译 | 示例
           

摘要

Separating halftones from text is an important step in document analysis. We present an algorithm that accurately extracts half-l tones from other information in printed documents. We treat halftone extraction as a texture-segmentation problem. We show that commonly used halftones, consisting of a pattern of dots, can be viewed as a texture. This texture exhibits a distinct spectral component that can be detected using a properly tuned Gabor filter. The Gabor filter essentially transforms halftones into high-contrast regions that can be easily segmented by thresholding. We propose a filter design procedure and pro vide experimental results. # 1997 Society of Photo-Optical Instrumentation Engineers. S0091-3286(97)02504-X Subject terms: halftones; spectral analysis: document analysis; Gabor filters; texture segmentation; texture analysis. Paper 32066 received June 24, 1996; revised manuscript received Nov. 9, 1996 accepted for publication Nov. 11, 1996.

著录项

  • 来源
    《Optical Engineering》 |1997年第6期|1044-1052|共9页
  • 作者单位

    The Pennsylvania State University Department of Computer Science and Engineering/ 103 Pond Laboratory University Park, Pennsylvania 16802 E-mail: dunn @ cse.psu.edu;

    University of North Carolina at Charlotte Department of Electrical Engineering/ Charlotte, North Carolina 28223;

    The Pennsylvania State University Departments of Electrical Engineering, Computer Science and Engineering, and Bioengineering/ 209F Electrical Engineering West University Park, Pennsylvania 16802;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 英语
  • 中图分类 光学仪器;
  • 关键词

获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号