Context-Adapted Document Segmentation Based on Multi-State Hidden Markov Tree Models in the Wavelet Domain

SONG Jin-ping; HOU Yu-hua; YANG Xiao-yi; TANG Yuan-yan

您当前的位置：

首页 >

文章列表页 >

Context-Adapted Document Segmentation Based on Multi-State Hidden Markov Tree Models in the Wavelet Domain

更新时间：2025-07-16

- Context-Adapted Document Segmentation Based on Multi-State Hidden Markov Tree Models in the Wavelet Domain
- Acta Electronica Sinica Vol. 35, Issue 1, Pages: 118-122(2007)
- 作者机构：
  
  1. 河南大学数学与信息科学学院,河南,开封,475004
  2. 河南大学应用数学所,河南,开封,475004
  3. 香港浸会大学,香港
  4. 河南大学数学与信息科学学院河南开封,475004
  5. 河南大学应用数学所河南开封,475004
  6. 香港浸会大学香港
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN911.73
- Published：2007
- 稿件说明：
移动端阅览
SONG Jin-ping, HOU Yu-hua, YANG Xiao-yi, et al. Context-Adapted Document Segmentation Based on Multi-State Hidden Markov Tree Models in the Wavelet Domain[J]. Acta Electronica Sinica, 2007, 35(1): 118-122.
DOI：

SONG Jin-ping, HOU Yu-hua, YANG Xiao-yi, et al. Context-Adapted Document Segmentation Based on Multi-State Hidden Markov Tree Models in the Wavelet Domain[J]. Acta Electronica Sinica, 2007, 35(1): 118-122. DOI：

摘要

本文针对文本图像首先提出了一种基于小波域多状态隐马尔科夫树模型的自适应文本图像分割算法(Context-Adapted wavelet-domain Hidden Markov Tree

简称为CAHMT)

该算法具有较高的分割质量和较低的计算复杂度.其次

为了进一步提高CAHMT算法分割的效果

将该算法与微分算子、尺度系数相结合提出了两种新的文本图像分割算法.最后通过实例阐明了这些算法的有效性.

Abstract

This paper presents a new document segmentation algorithm

called context-adapted wavelet-domain hidden Markov tree (CAHMT) model

which extends a recently emerged wavelet-domain hidden Markov tree (HMT) model[1].The proposed CAHMT can achieve more accurate quality in document segmentation with low computation complexity.In addition to further improving the segmenting performance

we combine differential operator and the lowest frequency subband (called scale coefficients in wavelet transform) with CAHMT and produce much better visually segmentation quality than the HMT does.

关键词

Keywords

references

Views

1170

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Lightweight MR Image Reconstruction Network Based on Wavelet Domain Complex Convolution and Complex Transformer

FD-GAN: Frequency-Decomposed Generative Adversarial Network for Unpaired Underwater Image Enhancement

ECG Motion Artifact Filtering Based on Two-Stage Adaptive Threshold Rules

Research on Multi-Channel Blind Electromagnetic Radiation Field Separation Method

SAR Image Despeckling Based on the Estimation of Speckle Variance in Nonsubsampled Contourlet Domain

Related Author

ZHANG Xiao-hua

LIAN Qiu-sheng

NIU Yu-zhen

ZHANG Ling-xin

LAN Jie

XU Rui

KE Xiao

LÜ Jian-hang

Related Institution

School of Information & Science and Engineering, Yanshan University

School of Mathematics and Information Science & Technology, Hebei Normal University of Science & Technology

Hebei Key Laboratory of Information Transmission and Signal Processing

College of Computer and Data Science, Fuzhou University

College of Electrical Engineering and Automation， Fuzhou University

⁰