-
公开(公告)号：US07949186B2
公开(公告)日：2011-05-24
申请号：US11724571
申请日：2007-03-15
Applicant: Kristen Grauman , Trevor Darrell
Inventor： Kristen Grauman , Trevor Darrell
CPC classification number: G06K9/6269 , G06K9/4671 , G06K9/6212
Abstract: A method for classifying or comparing objects includes detecting points of interest within two objects, computing feature descriptors at said points of interest, forming a multi-resolution histogram over feature descriptors for each object and computing a weighted intersection of multi-resolution histogram for each object. An alternative embodiment includes a method for matching objects by defining a plurality of bins for multi-resolution histograms having various levels and a plurality of cluster groups, each group having a center, for each point of interest, calculating a bin index, a bin count and a maximal distance to the bin center and providing a path vector indicative of the bins chosen at each level. Still another embodiment includes a method for matching objects comprising creating a set of feature vectors for each object of interest, mapping each set of feature vectors to a single high-dimensional vector to create an embedding vector and encoding each embedding vector with a binary hash string.
Abstract translation: 用于分类或比较对象的方法包括检测两个对象内的感兴趣点，在所述兴趣点处计算特征描述符，为每个对象的特征描述符形成多分辨率直方图，并且计算每个对象的多分辨率直方图的加权交集 。 替代实施例包括一种用于通过为具有各种级别的多分辨率直方图和多个群集组定义多个分块来匹配对象的方法，每个群组具有针对每个兴趣点的中心，计算bin索引，bin计数 以及与仓中心的最大距离，并提供指示在每个级别选择的仓的路径向量。 另一个实施例包括一种用于匹配对象的方法，包括为每个感兴趣对象创建一组特征向量，将每组特征向量映射到单个高维向量以创建嵌入向量并且使用二进制散列字符串对每个嵌入向量进行编码 。
-
公开(公告)号：US20070217676A1
公开(公告)日：2007-09-20
申请号：US11724571
申请日：2007-03-15
Applicant: Kristen Grauman , Trevor Darrell
Inventor： Kristen Grauman , Trevor Darrell
CPC classification number: G06K9/6269 , G06K9/4671 , G06K9/6212
Abstract: A method for classifying or comparing objects includes detecting points of interest within two objects, computing feature descriptors at said points of interest, forming a multi-resolution histogram over feature descriptors for each object and computing a weighted intersection of multi-resolution histogram for each object. An alternative embodiment includes a method for matching objects by defining a plurality of bins for multi-resolution histograms having various levels and a plurality of cluster groups, each group having a center, for each point of interest, calculating a bin index, a bin count and a maximal distance to the bin center and providing a path vector indicative of the bins chosen at each level. Still another embodiment includes a method for matching objects comprising creating a set of feature vectors for each object of interest, mapping each set of feature vectors to a single high-dimensional vector to create an embedding vector and encoding each embedding vector with a binary hash string.
Abstract translation: 用于分类或比较对象的方法包括检测两个对象内的感兴趣点，在所述兴趣点处计算特征描述符，为每个对象的特征描述符形成多分辨率直方图，并且计算每个对象的多分辨率直方图的加权交集 。 替代实施例包括一种用于通过为具有各种级别的多分辨率直方图和多个群集组定义多个分块来匹配对象的方法，每个群组具有针对每个兴趣点的中心，计算bin索引，bin计数 以及与仓中心的最大距离，并提供指示在每个级别选择的仓的路径向量。 另一个实施例包括一种用于匹配对象的方法，包括为每个感兴趣对象创建一组特征向量，将每组特征向量映射到单个高维向量以创建嵌入向量并且使用二进制散列字符串对每个嵌入向量进行编码 。
-
公开(公告)号：US06343150B1
公开(公告)日：2002-01-29
申请号：US09199799
申请日：1998-11-25
Applicant: Trevor Darrell , Michele M. Covell
Inventor： Trevor Darrell , Michele M. Covell
IPC: G06K900
Abstract: A given point of interest in an image is defined by two properties, a local attribute, such as color, and a neighborhood function that describes a similarity pattern. The color value is not influenced by nearby background regions of the image, and functions as a descriptor for each location. The neighborhood function distinguishes locations of similar color from one another, by capturing patterns of change in the local color. The neighborhood function measures the similarity between the local color and colors at nearby points, and reduces the measured similarity values that lie beyond contrast boundaries. Through the computation of such a transform for points of interest in an image, corresponding points in other images can be readily identified.
Abstract translation: 图像中的给定兴趣点由两个属性，诸如颜色的局部属性以及描述相似性模式的邻域函数来定义。 颜色值不受图像的附近背景区域的影响，并且用作每个位置的描述符。 邻域功能通过捕获局部颜色的变化模式来区分相似颜色的位置。 邻域函数测量附近点的局部颜色和颜色之间的相似度，并减少超出对比边界的测量相似度值。 通过对图像中的兴趣点的这种变换的计算，可以容易地识别其他图像中的相应点。
-
-
Search Results
13
records
(took 0.018 seconds)
