分类

The popular methods of remote sensing image classification have been generally analyzed and summarized. And the main methods are classification based on statistic, neural network classification, fuzzy classification, decision tree classification, expert system classification. Finally, the characters of each method have been summarized.

现综合分析了目前主要的遥感图像分类方法，将遥感图像分类方法归纳为：基于传统统计分析的分类方法、神经网络分类方法、模糊分类方法、决策树分类方法、专家系统分类方法，并对各种方法的应用情况进行了综述，并总结出各种分类方法应用特点。

International classification of diseases is the standardized classification of medical information that is accepted all over world currently. However, there are still many problems of ICD in our country. The quality of ICD should be promoted and improved. Reinforcing the knowledge training of ICD in doctors, professional training of ICD and the sense of responsibility training in codifier is an important way to improve the quality of ICD.

国际疾病分类是目前国际公认的卫生信息标准分类，但是由于我国的ICD分类工作开展的时间还不是很长，推广还不够广泛和深入，目前我国应用ICD分类还存在很多问题，ICD分类质量有待进一步提高和完善，加强临床医师的ICD分类知识培训和编码人员的专业培训及责任心教育是提高ICD分类质量的重要途径。

The contents included the followings : Nomenclature of trees , History of dendrology taxonomy , System of classification , Influences and fruit , Terms of taxonomy , Classification of tree farms , Classification of Gymnosperm , Classification of Angiosperm.

其内容如下：树木的命名、树木分类的历史、分类系统、花序及果实、分类的术语、木本蕨类之分类、裸子植物之分类与被子植物之分类。

Using a large data set of 1 894 images,we examine whether the colorspace transformation can increase the compactness of skin distribution and the discriminability between skin and nonskin distributions in fourteen 3D colorspaces and fourteen 2D chrominance planes.

比较结果表明：(1)颜色空间的变换并不能改善肤色紧致性、肤色-非肤色可分辨性以及分类等性能，但RGB及线性变换空间却具有较好的类可分辨性和分类性能；(2)去除亮度信息将明显降低肤色和非肤色之间的可分辨性和分类性能；(3)Bayes决策下的3维SPM的分类性能是最优和空间无关的，而其余分类器则普遍存在类似的"空间偏好性"；(4)同时采用肤色和非肤色模型的分类器的分类性能优于仅使用肤色模型的分类性能。

Algorithm named OVAWWT are presented to improve the equitableness and the precision of classifiers, a multiclassifier of SVMlight named MSVMlight based on the OVAWWT strategy is implemented, and two experiments on CWT100G data set are constructed, one to compare MSVMlight with other classifiers, and the other to compare WRCut strategy with RCut strategy.

多元分类器通常需要在训练时间和分类精度之间折衷。提出了加权阈值策略和一对多分类方法的改进算法 OVAWWT，以增加结果融合的公平性，从而提高分类精度。基于OVAWWT策略和SVMlight二元分类器，实现了基于SVMlight的多元分类器MSVMlight。

With the analysis of the features of tree system,potential aspects which could influence tree classification results are studied,the factors that should be taken into consideration in modelling hibernal tree classification are proposed and are concluded to six main aspects of features,amongst them the most correlated contents and information for classification are picked up to set up hibernal trees classification model,and finally implements the classification model with Bayes,which accomplishes a hibernal tree classification system based on Bayes.

通过分析树木体系的特征，研究并分析了可能影响树木分类结果的几个方面，提出了树木分类建模时应该考虑的因素，并将其归纳为六个方面，从中抽取与分类最相关的内容和信息，构建了冬态树木分类的模型，最后用贝叶斯方法实现了该分类模型，完成了基于贝叶斯的冬态树木分类系统。

Many classifieres for Web document classification are presented. Some of them are more accurate than others, and some provide more interpretable models, but none of them can combine the two beneficial properties.

在现有的Web文档分类器中，有的分类器产生比较精确的分类结果，有的分类器产生更易解释的分类模型，但还没有分类器可以将两个方面的优点结合起来。

In the case study of Plain, the TM image was processed with Tasseled Cap, Principal component analysis and Normalized Difference Vegetation Index extraction, prieror to vegetation classification, The imageries after preprocessing were use to identify the vegetation combined with original TM bands.

对平原地区的植被分类研究，首先对获取的TM影像进行Tasselled Cap处理、PCA处理和NDVI植被指数提取，处理后的各影像与TM原始六个波段影像一起用于植被遥感分类。分类采用监督分类和非监督分类方法，其中TC处理、PCA处理、NDVI影像、TM1-5，7组合影像采用非监督分类，原始TM6波段组合影像和TM3、4、5三波段组合影像采用监督分类。

Customes can gain the information of measuring cloth in "How to measure the cloth" section ( on the right handside of home page, under "文章分类" section).

顾客可以在& How to measure the cloth &单元中（在主页的右上部的&文章分类&部分）中找到如何量衣的相关知识。

It transforms the subtractive image from RGB color space to SRG color space. The experiment shows that it is efficient to segment the shadow with the moving vehicles.Secondly, in the vehicle classification module, we process the subtractive image by the morphological filtering and connected component labeling, obtain the figure and position of moving vehicle, and decide the characteristic vectors.At last, two vehicle classifiers are designed, one is the RBFNN classifier based on fuzzy K-means clustering, the other is the RBFNN classifier based on immune algorithm.

在车型分类方面，首先对差分图像作形态学滤波和区域连通处理，得到运动车辆的位置和轮廓，根据分类标准提取出车型分类所需的特征向量，然后分别用两种方法设计出车型分类器，一种是基于模糊K-均值聚类的RBF网络车型分类器，另一种是基于免疫算法的RBF网络车型分类器，通过在相同环境下的实验对比分析，基于免疫算法的RBF网络车型分类器在分类准确性和速度方面都优于基于模糊K-均值聚类的RBF网络车型分类器。

Breath, muscle contraction of the buttocks; arch body, as far as possible to hold his head, right leg straight towards the ceiling (peg-leg knee in order to avoid muscle tension).

呼气，收缩臀部肌肉；拱起身体，尽量抬起头来，右腿伸直朝向天花板（膝微屈，以避免肌肉紧张）。

The cost of moving grain food products was unchanged from May, but year over year are up 8%.

粮食产品的运输费用与5月份相比没有变化，但却比去年同期高8％。