First, this paper st udies those visual features which have be en usually implemented in image correspondence including multi-scale features.
首先，本文研究了在图像配准中常用的一些视觉特征，其中包括多尺度的特征。
By using box dimension, information dimension and correlation dimension, fractal features of Wuyishan Natural and Culture Heritage were studied at a multi-dynamic scale.
利用分形理论中的计盒维数、信息维数和关联维数，采取变换取样空间的方式研究了武夷山双遗产地景区系统分形特征的多尺度效应。
Based on the above, ocean fronts's multi-denoted and ocean fronts's features distribution on serial scale space are analyzed and the extracting ocean fronts by the optimal scale is discussed.
在此基础上分析了海洋锋的多尺度表达和海洋锋信息在各个尺度间的分布特征，并探讨了利用最佳尺度进行海洋锋提取的可行性。
According to this correlation and the features of the degradation images by fog the method of multi-scale process was used in this paper.
针对这种相关性，并结合薄雾退化图像的特点，采用了一种多尺度的处理方法，对处理后的图像采用自适应中值滤波器滤除噪声。
These are the names for features - some resembling geology, some not so much, for a large-scale multi-use residential project for Nanning, China.
这些名字都代表了中国南宁的一个混合功能大型居住项目的特色——有些与所在的地形类似，有些却不太相关。
According to face geometric features and statistical features, multi-scale wavelet fusing algorithm and SVM are respectively applied to get the location and size of candidate faces.
根据几何特征运用多尺度子波图像融合算法以及统计特征运用SVM方法分别得到人脸在图像中的位置和尺寸。
Firstly, texture and shape features are extracted at the pixel level, and spectral features are extracted at the object level based on multi-scale image segmentation maps.
首先在画素级上提取影像的纹理和形状结构特征，在构建的多尺度分割集影像上提取物件的区域光谱特征。
To extract texture features from medical images, the approaches for multi-scale complexity and multi-scale fractal dimension were proposed in this paper.
提出使用多尺度复杂性方法和多尺度分维数方法提取医学图像纹理特征并将之用于图像检索。
The features extract method of MCSF based on wavelet multi-scale transform is that the image feature of coefficient sub-frequency is decomposed with 3 layer of wavelet multi-scale transform.
基于小波多尺度分解子带主成份的特征提取法，利用小波多尺度分解子带系数图像特征。
Edge detction based on wavelet multi-scale identity is made. The statistics features based on regional gray and the co-occurrence matrix of gray level are taken as performing image segmentation.
该系统先对粮虫图像进行小波边缘提取，根据灰度共生矩阵和局部统计方法提取小波分割后的图像纹理特征。
Firstly, the method decomposes the coke micrograph with WBCT for multi-scale and multi-direction, and extracts the statistical features from each sub-band.
首先，运用WBCT对图像进行多尺度多方向分解，提取出各子频带的统计特征量；
Firstly, the method decomposes the coke micrograph with WBCT for multi-scale and multi-direction, and extracts the statistical features from each sub-band.
首先，运用WBCT对图像进行多尺度多方向分解，提取出各子频带的统计特征量；
应用推荐