Compared with conventional statistic classifier , the artificial neural network ( ann ) has been developed and applied to remote sensing data classification problem , which does n ' t need suppose parameterized distribution of sample space in advance 与传统统计方法的分类器相比较，人工神经网络法不需要预先假设样本空间的参数化统计分布，正在被越来越普遍的应用于遥感图像分类的研究。
In order to improve the accuracy of remote sensing image classification and compensate the weakness of maximum likelihood classifier , this paper puts forward a new classification method , which is based on support vector machine ( svm ) 摘要为了提高遥感图像分类的精度，弥补传统最大似然分类方法所固有的分类时样本不足的缺陷，提出了一种基于支持向量机、光谱特征和纹理特征相结合的遥感图像分类方法。
This chapter first introduces the principium of trellis coded vector quantization , then focuses on analyzing the algorithm of wavelet image classified weighted tcvq and its realization process , also gives tcvq application to wavelet image coding and its simulation results 首先分析了网格编码矢量量化的原理，在第三章矢量量化的基础上详细介绍了小波图像分类加权tcvq算法的原理和实现过程，并给出了tcvq在小波图像量化中的应用实例和仿真结果。
We choose 80 vectors of 40 channels and save them in handwriting database . ( 5 ) we use a weighted euclidean distance ( wed ) classifier and k - nearest neighbor ( k - nn ) classifier to fulfill the identification task . the eigenvectors are recorded in different handwriting database with text format ( 5 )论文对笔迹图像分类器进行了设计，通过加权欧式据立法和k -近邻算法对笔迹样本进行分类匹配，将训练后的80维特征向量以纯文本格式保存于不同的笔迹模式库中。
In this paper we studied the textural features extraction , remote sensing images classification and bp neural network techniques and their applications in the meteorological problems such as recognition of the cloud cluster feature , cloud - drift wind retrieval and heavy rain process analysis etc . to the question of the low precise recognition of satellite images by using spectral features , the proposed approach assumes to perform a multiple analysis based on an advisable decision - making model by first developing a mixed pixel model which was based on the textural features of images , and then improving the recognition intelligence 本文对模式识别领域中的图像纹理特征提取、遥感图像分类、 bp神经网络与纹理特征组合分类等方法，以及它们在云团属性识别、云迹风反演和暴雨过程分析等气象问题中的应用作了研究。针对过去利用图像光谱亮度特征进行识别分析气象卫星图像准确度不高的问题，本文提出了发展混合像元的分解模型，以图像的纹理特征为基础，提高图像识别的智能水平，以实现在分析决策模型的支持下，快速准确的复合分析的解决方案。
This paper mainly discusses the topic of decision fusion of the processing results of multi - band sar images , including the target detection algorithm , the classification algorithm and the decision fusion algorithms . there are not only homogenous regions but also nonhomogenous regions in sar images 本文从应用要求出发,分别研究了多波段sar目标检测、基于neyman - pearson准则的决策级融合算法、多波段sar图像分类算法和dempster - shafer证据理论决策级融合算法。
