Wavelet Transform Based Multiscale Hurst Parameter Texture Features and Its Application

Li Yan; Peng Jia-xiong

您当前的位置：

首页 >

文章列表页 >

Wavelet Transform Based Multiscale Hurst Parameter Texture Features and Its Application

更新时间：2025-07-16

- Wavelet Transform Based Multiscale Hurst Parameter Texture Features and Its Application
- Acta Electronica Sinica Vol. 30, Issue 7, Pages: 1041-1043(2002)
- 作者机构：
  
  1. 华中理工大学图像识别与人工智能研究所图像信息处理与智能控制教育部重点实验室,湖北,武汉,430074
  2. 北京大学视觉与听觉信息处理实验室,北京,100871
  3. 华中理工大学图像识别与人工智能研究所图像信息处理与智能控制教育部重点实验室湖北武汉,430074
  4. 北京大学视觉与听觉信息处理实验室北京,100871
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391
- Published Online：25 July 2002，
  
  Published：2002
- 稿件说明：
移动端阅览
Li Yan, Peng Jia-xiong. Wavelet Transform Based Multiscale Hurst Parameter Texture Features and Its Application[J]. Acta Electronica Sinica, 2002, 30(7): 1041-1043.
DOI：

Li Yan, Peng Jia-xiong. Wavelet Transform Based Multiscale Hurst Parameter Texture Features and Its Application[J]. Acta Electronica Sinica, 2002, 30(7): 1041-1043. DOI：

摘要

扩展的自相似模型(ESS)是一种广义的分数布朗运动模型(fBm)

它的多尺度H参数与粗糙度之间是对应的

因为不要求粗糙度的尺度不变性

所以能够区分大多数自然纹理.它的结构函数计算是基于图像在一定尺度上的灰度差

这可以用小波变换低频分量的一阶差分去定义.由于小波变换具有抑制噪声的能力

由此导出的特征具有更好的抗噪性能.实验证明对卫星遥感图像达到了较高的分类正确率.同时也说明

纹理的自相似特性在低频分量上的体现更突出.

Abstract

The Extended self-similar model(ESS)is a general fractional Brownian motion(fBm) model.Its multiscale Hurst parameters have relations with roughness.In the meantime

it doesn't require the roughness to be scale-invariant as fractal dimensions do.The multiscale Hurst parameters can discriminate a large number of natural textures and are suitable to be used for texture classification.Its structure function is based on the difference of the gray levels at some scale.This can be defined by the difference of the lower subband signal.Because wavelet transform has the ability of reducing the noise

the derived features performed better.Our experiments show that higher rate of correct classification to SPOT image is obtained.In the meantime it shows that the texture's self-similarity is more evident in lower subband than that in gray level.

关键词

Keywords

references

Views

1188

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