In this paper, a classification algorithm based on multi-threshold binary encoding for Description of Spectral Shape is introduced, and result of image experimentation is present.
本文提出一种基于光谱形状描述的多门限的二进制编码分类方法，并给出了图象实验的结果。
Classification of mass spectra of toxic compounds is based on the numerical features derived from spectral data.
有毒化合物质谱分类是以光谱数据的数值特性为基础的。
The logic function classification with spectral coefficients is discussed and the definition of characteristic threshold logic function is given.
讨论了逻辑函数的谱系数分类，给出了特征阈值逻辑函数的定义。
In this paper, we studied the spectral character of our study region in detail and based our classification system on the spectral character and our filed work.
仔细分析了研究区典型地物的光谱特征和同物异谱与异物同谱现象，并结合实地考察建立了分类体系。
Compared with the classification method purely based on spectral character, this method can improve the classification accuracy and refine object classes in some extent.
与单纯基于光谱特征的分类方法进行比较，该方法在一定程度上改善了分类精度，细化了地物类别。
A convenient classification of stars is based upon the observed sequence of spectral types.
一种实用的恒星分类法是基于测得的光谱类型序列。
This paper deals with statistical analysis method and spectral analysis method for classification of sea bed using side scan sonar data.
本文对用侧扫声纳信号进行海床类型识别的统计分析法和频谱分析法进行探讨。
According to the rice spectral features of hyperspectral image data acquired during the rice is growing, a hybrid decision tree classification algorithm dealing with the variety of rice is developed.
根据水稻生长期的高光谱数据的光谱特征，设计了一个混合决策树分类算法。
Finally, according to the restriction of the preliminary clustering result derived from spectral feature of objects, the ultimate classification is achieved referring to the rules.
最后，在对象光谱特征的初步分类结果，根据纹理分类规则得到最终结果基础上。
In corresponding to different sensor spectral characteristics, many classification methods for snow mapping were developed.
对应不同传感器件的光谱特征，多种分类方法被相继提出。
The aim of this paper is to study classification approach of topographical objects with Multi-spectral image.
本论文研究利用多光谱图像进行自然地物目标分类技术。
It is concluded that the fusion of high spatial imagery and multi-spectral bands can enhance change information, and the fusion of texture character can improve the classification results.
通过高几何分辨率图像与多光谱波段融合方法可以，增强变化信息，纹理特征参与变化信息提取可以提高变化类型的分类精度。
Based on the spectral feature neighborhood, this paper proposes a tolerant rough set classification method to handle the uncertainty in the process of satellite remote sensing data classification.
结合粗糙集理论和遥感数据中地物光谱特征空间分布信息，提出了一种基于光谱特征邻域的容差粗糙集分类方法，用来处理卫星遥感数据分类中的不确定性问题。
The road density index analysis has two ways: the post-classification compare method based on spectral-spatial structure and the imagery difference method based on spectral-spatial structure.
道路密度指数分析法有两类方法：基于光谱—空间结构的分类后比较法和基于光谱—空间结构的图像差值法。
In addition, the spectral selection based on the image's feature and experience is also an effective way to improve the classification of hyper-spectral remote sensing images.
另外，根据图像特征和经验对图像进行波段选择，也是改善高光谱遥感分类效果的有效途径。
Unfortunately, in hyper-spectral image classification, training samples are usually limited.
然而在高光谱图像分类中，训练样本通常是有限的。
The temporal and spectral information has influence upon classification precision, and this can't be ignored in crop classification.
并且这些算法忽视了时相信息在作物分类中的作用，更没有把时相和波谱信息进行合理的组合。
The temporal and spectral information has influence upon classification precision, and this can't be ignored in crop classification.
并且这些算法忽视了时相信息在作物分类中的作用，更没有把时相和波谱信息进行合理的组合。
应用推荐