非监督分类

双波段全极化SAR图像非监督分类方法及实验研究

Unsupervised Classification Methods and Experimental Research of Dual-frequency Fully Polarimetric SAR Images

基于H-α和改进C-均值的全极化SAR图像非监督分类

Unsupervised Classification of Fully Polarimetric SAR Image Using H - α Decomposition and Modified C-Mean Algorithm

基于全极化SAR非监督分类的迭代分类方法

The Iteration Classification Method and Experiment Study Based on Unsupervised Classification of Fully Polarimetric SAR Image

文章提出了一种新的基于遗传策略和模糊ART（AdaptiveResonanceTheory）神经网络的非监督分类方法。

A new unsupervised classification method using evolutionary strategies and fuzzy ART ( adaptive resonance theory ) neural networks is proposed in this paper .

基于多通道Gabor滤波器的纹理图像非监督分类

Unsupervised Texture Segmentation Via Multi-channel Gabor Filters

随着对极化SAR（syntheticApertureRadar）图像分类研究的深入，近年来许多监督和非监督分类方法被相继提出。

With the deep research of the polarimetric SAR ( Synthetic Aperture Radar ) image classification , many supervised and unsupervised classification methods have been proposed one after another in recent years .

本文在全极化合成孔径雷达（SAR）特征分解和最大似然估计（ML）分类的基础上，提出基于全极化SAR极化特征分解及最大似然估计的非监督分类迭代算法。

Based on the theory of eigen-decomposition of fully polarimetric Synthetic Aperture Radar ( SAR ) and maximum likelihood ( ML ) classifier , an unsupervised iteration classification method is proposed .

接着详细分析了SAR图像中相干斑的形成机理及其数学描述和统计特性，实现并分析了经典的相干斑抑制算法和基于极化分解的极化SAR非监督分类算法。

Analysis the SAR image speckle formation mechanism , mathematical description and statistical properties detailedly . Then summarize the classical polarization SAR speckle reduction algorithms and non-supervised classification algorithms based on polarimetric decomposition .

利用美国陆地卫星的TM图像资料，对山东省桓台县和垦利县TM图像资料进行计算机几何校正和不同的增强处理，以分类和非监督分类两种方法提取耕地信息。

The TM image materials of Huantai County and Kenli County were emendated geometrically and enhanced differently , and the farm land information was derived by supervised classification and unsupervised classification .

利用1996年和1986年秋季陆地卫星TM数据，将计算机监督分类与非监督分类识别方法结合应用进行草地的解译，改进算法，改善遥感图像的识别精度。

Grasslands had been revised with the method combined supervised and non-supervised classifications using Landsat data in autumn of 1996 and 1986 . The advanced algorithm was used to improve the accuracy .

同时应用传统的监督分类方法（最小距离法和SAM法）和非监督分类方法（K-均值法和ISODATA法）进行分类。

Traditional supervised classification method ( Minimum Distance and Maximum Likelihood ) and unsupervised classification method ( K-Means and ISODATA ) were also used in this paper .

在用TM遥感图像对土壤类型进行非监督分类的基础上，建立了正向推理与逆向推理相结合的推理机制，对土壤类型进行分类识别决策。

On the basis of non_supervising classification for soils with TM images , the author discusses the reasoning mechanism by combining the direct inference combined with inverse reasoning for soil classification and recognition decision .

利用1998年9月28日TM卫星数据，经过数据校正、影像增强和非监督分类等处理，制作卫星影像分类图，建立判读标志；

Landsat / TM image data was used as data source in the study , and the image data was processed with the support of the methods-geometric correction , spatial enhancement and unsupervised classification .

深入讨论了基于H-α分割的Wishart非监督分类方法在农作物分类中的性能；

The performance of Wishart classification for crops based on H - α segmentation plane is discussed in detail firstly .

对1999年的Landsat-TM进行非监督分类，得到1999年的植被分布图。

Direct unsupervised classification is made to 1999 Landsat-TM image , and gets the 1999 vegetation distribution image .

在论文中，详细介绍了传统的非监督分类方法K&means算法及ISODATA算法，并在此基础上，提出了基于概率模型的K-means算法和模糊ISODATA算法。

In the paper , the traditional un-supervised classification such as K-means , Isodata are shown detailedly . Based on this , K-means in the Gauss distribution , Rayleigh distribution and fuzzy Isodata are introduced .

通过对福州市TM图像资料进行几何校正和不同的增强处理，以监督分类和非监督分类两种方法提取人工建筑物信息，并与目视解译相比较。

The TM image material of Fuzhou city were emendated geometrically and enhanced differently , and the artificial building information was derived by supervised classification and unsupervised classification , at the same time , those information were compared with the result of translated by eyes .

利用ERDAS的非监督分类和监督分类对遥感影像进行解译，结合实地调查生成了周边地区土地利用类型图；

Translated the remote sensing reflection and investigated the spot by unsupervised classification and supervised classification of ERDAS . As a result , the periphery district land utilization type picture was generated .

取1990年、1995年、2000年和2005年4个时相覆盖广州市的TM遥感影像为数据源，经非监督分类及人工目视解译，获得研究区各时相土地覆被类型图。

Four TM remote sensing images of Guangzhou in 1990 , 1995 , 2000 and 2005 were taken as data for the present study . The images fully covered the area of Guangzhou . The data sources of land-cover landscape were translated under manual and un-supervised interpretations with GIS software .

对不同分区进行非监督分类研究，根据地面状况确定非监督分类初次分类数、参考2004年目视解译结果确定自动分类重编码（Recode）方式，分类精度达到60～70%；

· Unsupervised classification was explored in each subarea , and the feasible number of the first classification and the appropriate way of recoding were fixed while the precision can reach 60-70 % .

实验结果表明基于BDSET和FDSET融合的分类方法比传统的非监督分类方法具有更好的分类效果，有效地提高了分类的精度。

The experimental results show that these two classification methods of multi-sources information fusion can result in better accuracy than that of conventional unsupervised classification method .

本文通过运用ASTER遥感影像数据，对不同地物进行光谱分析，根据不同地物在不同波段的光谱特征曲线，分别提取植被和水体信息，然后进行非监督分类。

In this paper , ASTER image was used to analyze the spectral characteristics of different ground objects . According to the spectral characteristic curves of different ground objects in different bands , the information on plants and water bodies were picked up , and unsupervised classification was carried out .

通过监督分类和非监督分类估算了洪水淹没范围；

The inundated area is estimated by supervised and unsupervised classification ;

非监督分类中初始聚类中心法的比较研究

The comparative research of initializing cluster centers for unsupervised classification

模糊聚类是非监督分类中的一类重要方法。

Fuzzy clustering is an important method in unsupervised classification .

基于遗传策略和神经网络的非监督分类方法

The Unsupervised Classification Using Evolutionary Strategies and Neural Networks

多相位水平集高分辨率遥感影像非监督分类

Unsupervised Classification of High Resolution Remote Sensing Imagery Using Multiphase Level Set Method

其中，传统的沙化信息提取技术包括监督与非监督分类法及目视解译法；

The former incorporate supervision and non-supervision classification methods and visual interpretation methods ;

一种模型选择优化准则及其在高光谱图像非监督分类中的应用

An Unsupervised Classification Method Based on a Model Selection Criterion for Hyperspectral Data

通过改进采样方法，在非监督分类生成的初始训练样本的基础上，进行删除、增补、合并等样本调整，使训练样本的选取精度大大提高，明显提高了分类精度。

By improving the signature selection accuracy , this method improves classification accuracy greatly .