According to the color spatial feature of an image, a new algorithm based on entropy is proposed.
针对图像颜色的空间分布特征，提出了一种新的基于熵的表示方法。
Traditionally image retrieval mainly relies on single feature such as color, texture, shape and spatial relationship, etc., so the result is usually not so good.
传统的基于内容的图像检索主要依赖颜色、纹理、形状、空间关系等单一视觉特征，检索效果往往不够理想。
And the image feature descriptor has a rotation, translation, scaling invariance, etc. it can be a very good to describe the shape and spatial distribution of information.
且获得的图像特征描述符具有旋转、平移、尺度不变性等优点，能够很好地描述图像的形状和空间分布信息。
Segmentation Based in Spatial Information (SS) can segment an image into different regions by the feature of hue in the single frame.
空间分割利用图像单帧的灰度信息将图像分割成不同的区域。
This paper presents a trade mark retrieval method in which the shape feature and spatial relationship are both used for the purpose of making full use of image info and improving retrieval precision.
为了充分利用商标图象的内部信息，以提高商标图象的检索精度，提出了一种综合利用商标形状特征与其内部空间位置关系特征来检索二值商标图象的方法。
A product correlation algorithm of image registration based on feature and spatial-temporal correlation was presented.
提出了基于特征和时空关联的积相关图像匹配算法。
It must be stressed that spatial relations and feature similarity are two indispensable aspects of reliable image registration, and both are of equivalent importance.
应该说，特征空间关系一致性和特征属性相似性是进行可靠特征匹配不可或缺的两个方面，是同等重要的。
Deducing 3-d spatial image parameters according to 2-d section or the image parameters on projecting plane. the required feature informations are extracted and processed.
根据二维截面或投影面上的图象参数去推断三维的空间图象参数，提取需要的特征信息并自动地进行处理及输出特征参数值。
Deducing 3-d spatial image parameters according to 2-d section or the image parameters on projecting plane. the required feature informations are extracted and processed.
根据二维截面或投影面上的图象参数去推断三维的空间图象参数，提取需要的特征信息并自动地进行处理及输出特征参数值。
应用推荐