航空影像纹理分类和分割对常数C敏感；
The effect of C is large for aerial image segmentation and classification.
本文提出了一种遥感图像旋转不变纹理分类的新方法。
This paper puts forward a new method of invariant texture classification for remote sensing image.
方向场在指纹识别、纹理分类等领域有很重要的应用。
Orientation field plays an important role in the identification of fingerprints, taxonomy of texture and so forth.
针对马尔可夫随机场方法用于影像纹理分类进行了探讨。
This paper deals with markov random field and it's application in image texture classification.
纹理图像千变万化，目前在纹理分类上没有明确的标准。
Until now, we have no definite discipline to classify texture images because textures vary too much.
提出了一种基于函数联接的感知器神经网络的纹理分类方法。
This paper presents a texture classification approach based on function link network.
采用神经网络作为载体图像的纹理分类器，突出原始图像的纹理区。
While the ANN was used as the texture analyzer of the original image, the texture zone of the original image would be given prominently.
对方向性强的纹理，在进行旋转变换后，可以提高纹理分类的正确率。
The result suggested that the correct classification ratio be increased by rotative transformation for the textures with intense direction.
该算法利用纹理信息的频域分布以及尺度特性，并在此基础上进行纹理分类。
Based on frequency domain distribution and scale feature of textural information, we can do texture classification effectively.
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。
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.
介绍了一种利用自相关函数来估算图像分形维数的方法，并将其应用到木材的纹理分类检测中。
This paper introduced a method availing autocorrelation functions to estimate the image fractal dimension, and the method can detect classification of the wood texture.
通过对结果的分析得到一些结论，这些结论对于选用和搭配影像纹理分类方法有一定的指导作用。
This paper used three kinds of texture classification methods to classify aerial image. Through experiment and analysis, we get some Suggestions for choosing texture classification method.
将该方法与其它旋转不变纹理分类算法进行比较，实验结果表明，提出的算法能有效地提高正确分类率。
This method is compared with other rotation invariant texture classification algorithm, the experiment results show that it can improve the classification rate effectively.
对纹理图像进行的实验表明，采用这种方法能够提高学习速度，简化计算过程，纹理分类能取得较好的效果。
Experiment shows that better classification results can be obtained than traditional Euclidean distance method, and it has the advantages of simple processing procedure and fast convergence speed.
在基于小波的纹理分类算法的基础上，提出了逐点特征加权和活动窗口算法，使小波纹理分析能够用于高分辨率遥感影像的分类。
This paper discusses the shortage of conventional algorithms of texture classification based on wavelet transform, presents two improved approaches of point feature weighting and smart windows.
本文提出一种新的多分辨率纹理分类方法，该方法采用称为小波帧的冗余小波分解，从而获得具有稳定性和平移不变性的特征描述。
The method adopts redundant wavelet, which is called wavelet frame, to decompose and then to achieve the characteristic description of stability and translational constancy.
分析了有限脊小波变换可以实现图像的旋转不变性和平移不变性，提出了结合两种小波变换提取图像纹理特征的方法，实现了在小波域中进行图像的不变纹理分类。
A method using two wavelet transform to get the texture feature for remote sensing is put forward, in order to turn out the invariant texture classification for remote sensing in the wavelet domain.
内容涉及声图像的预处理、纹理和形状特征的提取，以及分类器的设计等。
The contents in the paper include acoustic image preprocessing, feature extraction of texture and shape, and classifier design.
为此，研究了利用分形理论对农作物病变叶片自然纹理图像进行了处理，利用BP网络来实现自然纹理图像的分类问题。
So, the problems, that utilize the theory of analyzing figure to dispose crop pathological changes laminate nature texture image, and utilize BP network to class nature texture image, are studied.
首先利用色度矩提取葡萄病害叶片纹理图像的特征向量，然后将支持向量机分类方法应用于病害的识别。
At first, extracting features of chromaticity moments of texture image of grape disease is done, then classification method of SVM for recognition of grape disease is discussed.
首先利用色度矩提取玉米病害叶片纹理图像的特征向量，然后将支持向量机分类方法应用于病害的识别。
At first, the extracting features of chromaticity moments of texture image of maize disease is done, then classification method of SVM for recognition of maize disease is discussed.
给出一种抽取纹理特征的算法，该算法实时性强，适于在线遥感图像分类。
This paper proposes a fast algorithm for texture feature extraction. The new algorithm is suitable for remote image classification on line.
使用这一方法挑选合适的纹理特征用于图像分类，并对结果进行分析。
Appropriate texture features are selected with this method to serve image classification and simulative results are discussed.
针对这种情况，提出了一种改进的特征提取方法，将基于原图像的灰度级共生矩阵提取的纹理特征与滤波后图像的灰度特征进行组合用于分类。
Accordingly, we propose an improved feature extraction scheme, adopting the tone of filtered image combined with the texture features based on the GLCM of unfiltered image to form the feature vector.
该方法将树型小波中颇纹理能量特征、灰度共生矩阵特征、树型小波滤波后的灰度组成的特征矢量对SAR图像进行分类。
The feature vector is composed of wavelet texture energy features, texture features based on the gray-level co-occurrence matrix and the tone of filtered SAR image by using tree wavelet.
提取有效的特征用于纹理描述和分类一直是纹理分析的难点。
Extracting effective features for texture description and classification is always a difficult problem in texture analysis.
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。
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.
使用本模型的七个纹理参数作特征，在六类地物类型210个样本上作实验，由此设计的分类器的识别率为98.6%。
Seven texture parameters of this model are used for classifying six types of remote sense image over 210 samples. It's success percent is 98. 6 %.
使用本模型的七个纹理参数作特征，在六类地物类型210个样本上作实验，由此设计的分类器的识别率为98.6%。
Seven texture parameters of this model are used for classifying six types of remote sense image over 210 samples. It's success percent is 98. 6 %.
应用推荐