Improving classification accuracy is always the focus for remote sensing image classification.

提高遥感图像分类精度一直是受到普遍关注的焦点问题.

In computer science terms, this is basically an image classification task.

用计算机科学术语来说，这基本上就是一个图像分类的事。

The accuracy of land vegetative cover index rested with the accuracy of image classification, but had no direct relations with total classification accuracy.

土地植被覆盖指数的准确度取决于图像分类准确度，但与分类总准确度没有直接关系。

Then support vector machines using the kernel are trained to perform image classification.

然后将该核函数应用于支持向量机，对图像进行分类。

To improve the precision of remote sensing image classification, this paper proposes hybrid multi - classifier combination method.

为改善遥感影像分类精度, 提出混合多分类器结合算法.

This paper proposes to use a patch-based local feature with spatial pyramid matching to encode its spatial information for automatic medical image classification.

本文提出采用基于图像子块的局部特征并利用空间金字塔结合特征的空间信息，用于医学图像的自动分类。

Experimental results demonstrate that the performance of image classification can be improved by the integration of kernel based measurements and the multi-level representation of visual words.

实验结果表明，将核函数度量同视觉单词的多层次描述结合在一起，能够显著提高图像的识别能力。