MULTISCALE 3D TEXTURE SYNTHESIS
    1.
    发明申请
    MULTISCALE 3D TEXTURE SYNTHESIS 审中-公开
    多尺度3D纹理综合

    公开(公告)号:WO2017194921A1

    公开(公告)日:2017-11-16

    申请号:PCT/GB2017/051277

    申请日:2017-05-09

    CPC classification number: G06T15/04 G06K9/6219 G06N3/08

    Abstract: The present invention relates to generating texture maps for use in rendering visual output. According to a first aspect, there is provided a method for generating textures for use in rendering visual output, the method comprising the steps of: generating, using a first hierarchical algorithm, a first texture from one or more sets of initialisation data; and selectively refining the first texture, using one or more further hierarchical algorithms, to generate one or more further textures from at least a section of the first texture and one or more sets of further initialisation data; wherein at least a section of each of the one or more further textures differs from the first texture.

    Abstract translation: 本发明涉及生成用于渲染视觉输出的纹理贴图。 根据第一方面,提供了一种用于生成用于呈现视觉输出的纹理的方法,所述方法包括以下步骤:使用第一分层算法从一组或多组初始化数据生成第一纹理; 以及使用一个或多个另外的分层算法来选择性地细化所述第一纹理,以从所述第一纹理的至少一部分和一组或多组另外的初始化数据生成一个或多个其他纹理; 其中所述一个或多个其他纹理中的每一个的至少一部分不同于所述第一纹理。

    PERFORMING VOCABULARY-BASED VISUAL SEARCH USING MULTI-RESOLUTION FEATURE DESCRIPTORS
    3.
    发明申请
    PERFORMING VOCABULARY-BASED VISUAL SEARCH USING MULTI-RESOLUTION FEATURE DESCRIPTORS 审中-公开
    使用多分辨率特征描述符执行基于VOCABULARY的视觉搜索

    公开(公告)号:WO2015023742A1

    公开(公告)日:2015-02-19

    申请号:PCT/US2014/050874

    申请日:2014-08-13

    Inventor: HAMSICI, Onur C.

    Abstract: In general, techniques are described for performing a vocabulary-based visual search using multi-resolution feature descriptors. A device may comprise one or more processors configured to perform the techniques. The processors may generate a hierarchically arranged data structure to be used when classifying objects included within a query image based on multi-resolution query feature descriptor extracted from the query image at a first scale space resolution and a second scale space resolution. The hierarchically arranged data structure may represent a first query feature descriptor of the multi-resolution feature descriptor extracted at the first scale space resolution and a second corresponding query feature descriptor of the multi-resolution feature descriptor extracted at the second scale space resolution hierarchically arranged according to the first scale space resolution and the second scale space resolution. The processors may then perform a visual search based on the generated data structure.

    Abstract translation: 通常,描述了使用多分辨率特征描述符执行基于词汇的视觉搜索的技术。 设备可以包括配置成执行技术的一个或多个处理器。 处理器可以生成分层布置的数据结构,以便在基于从第一尺度空间分辨率和第二尺度空间分辨率的查询图像提取的多分辨率查询特征描述符对包括在查询图像内的对象进行分类时使用。 层次排列的数据结构可以表示以第一尺度空间分辨率提取的多分辨率特征描述符的第一查询特征描述符和在第二尺度空间分辨率处提取的第二对应查询特征描述符, 到第一尺度空间分辨率和第二尺度空间分辨率。 然后,处理器可以基于生成的数据结构执行视觉搜索。

    IMAGE DEBLURRING
    4.
    发明申请
    IMAGE DEBLURRING 审中-公开
    图像消失

    公开(公告)号:WO2014169162A1

    公开(公告)日:2014-10-16

    申请号:PCT/US2014/033710

    申请日:2014-04-11

    Abstract: Image deblurring is described, for example, to remove blur from digital photographs captured at a handheld camera phone and which are blurred due to camera shake. An estimate of blur in an image is available from a blur estimator and a trained machine learning system is available to compute parameter values of a blur function from the blurred image. The blur function is obtained from a probability distribution relating a sharp image, a blurred image and a fixed blur estimate. For example, the machine learning system is a regression tree field trained using pairs of empirical sharp images and blurred images calculated from the empirical images using artificially generated blur kernels.

    Abstract translation: 描述了图像去模糊,例如,从在手持相机手机拍摄的数字照片中消除模糊,并且由于相机抖动而被模糊。 图像中的模糊估计可以从模糊估计器获得,并且经过训练的机器学习系统可用于从模糊图像计算模糊函数的参数值。 从与锐利图像,模糊图像和固定模糊估计相关的概率分布获得模糊函数。 例如,机器学习系统是使用经验锐利图像对和使用人为生成的模糊内核从经验图像计算的模糊图像训练的回归树字段。

    IMAGE LABELING USING GEODESIC FEATURES
    5.
    发明申请
    IMAGE LABELING USING GEODESIC FEATURES 审中-公开
    使用地理特征的图像标签

    公开(公告)号:WO2014168898A1

    公开(公告)日:2014-10-16

    申请号:PCT/US2014/033241

    申请日:2014-04-08

    Abstract: Image labeling is described, for example, to recognize body organs in a medical image, to label body parts in a depth image of a game player, to label objects in a video of a scene. In various embodiments an automated classifier uses geodesic features of an image, and optionally other types of features, to semantically segment an image. For example, the geodesic features relate to a distance between image elements, the distance taking into account information about image content between the image elements. In some examples the automated classifier is an entangled random decision forest in which data accumulated at earlier tree levels is used to make decisions at later tree levels. In some examples the automated classifier has auto-context by comprising two or more random decision forests. In various examples parallel processing and look up procedures are used.

    Abstract translation: 图像标记例如被描述为识别医学图像中的身体器官,以在玩家的深度图像中标记身体部位来标记场景的视频中的对象。 在各种实施例中,自动分类器使用图像的测地学特征以及可选地其他类型的特征来语义地分割图像。 例如,测地特征涉及图像元素之间的距离,该距离考虑了关于图像元素之间的图像内容的信息。 在一些示例中,自动分类器是纠缠的随机决策树,其中在较早的树级上累积的数据用于在稍后的树级别做出决定。 在一些示例中,自动分类器具有包含两个或更多个随机决策树的自动上下文。 在各种示例中,使用并行处理和查找过程。

    AUTOMATIC IMAGE PILING
    6.
    发明申请
    AUTOMATIC IMAGE PILING 审中-公开
    自动图像打桩

    公开(公告)号:WO2014163979A1

    公开(公告)日:2014-10-09

    申请号:PCT/US2014/019563

    申请日:2014-02-28

    Applicant: YAHOO! INC.

    CPC classification number: G06K9/6219 G06K9/00684 G06K9/4604

    Abstract: A system for determining piles comprises an interface and a processor. The interface is configured to receive an image. The processor is configured to determine one or more attributes of the image; to determine whether the image is a member of a top of a hierarchy based at least in part on the attributes. In the event it is determined that the image is a member of the top of the hierarchy,: determine a set of elements of the hierarchy the image is a member of, based at least in part on the attributes and determine which of the set of entities are piles.

    Abstract translation: 用于确定桩的系统包括接口和处理器。 该接口被配置为接收图像。 处理器被配置为确定图像的一个或多个属性; 以至少部分地基于属性来确定图像是层次结构的顶部的成员。 在确定图像是层次结构的顶部的成员的情况下:至少部分地基于属性来确定图像是其成员的层次结构的一组元素,并且确定该集合中的哪一个 实体是桩。

    INCREMENTAL IMAGE CLUSTERING
    7.
    发明申请
    INCREMENTAL IMAGE CLUSTERING 审中-公开
    增量图像聚类

    公开(公告)号:WO2013016837A1

    公开(公告)日:2013-02-07

    申请号:PCT/CN2011/001242

    申请日:2011-07-29

    CPC classification number: G06K9/6218 G06F17/30247 G06K9/6219

    Abstract: Methods, systems, and computer readable media with executable instructions, and/or logic are provided for incremental image clustering. An example method for incremental image clustering can include identifying, via a computing device, a number of candidate nodes from among evaluated leaf image cluster (LIC) nodes on an image cluster tree (ICT) based on a similarity between a feature of a new image and an average feature of each of the evaluated LIC nodes. The evaluated nodes include at least one node along each path from a root node to either a leaf node or a node having a similarity exceeding a first threshold. A most-similar node can be determined, via the computing device, from among the number of candidate nodes. The new image can be inserted to a node associated with the determined most-similar node, via the computing device.

    Abstract translation: 提供了具有可执行指令和/或逻辑的方法,系统和计算机可读介质用于增量图像聚类。 用于增量图像聚类的示例性方法可以包括基于新图像的特征之间的相似性,经由计算设备识别来自图像簇树(ICT)上的评估叶图像簇(LIC)节点中的候选节点的数量 以及每个评估的LIC节点的平均特征。 评估的节点包括沿着从根节点到叶节点或具有超过第一阈值的相似度的节点的每个路径的至少一个节点。 可以通过计算设备从候选节点的数量中确定最相似的节点。 可以通过计算设备将新图像插入到与所确定的最相似的节点相关联的节点。

    DETERMINING USER SIMILARITIES BASED ON LOCATION HISTORIES
    8.
    发明申请
    DETERMINING USER SIMILARITIES BASED ON LOCATION HISTORIES 审中-公开
    根据位置历史确定用户类似

    公开(公告)号:WO2010062726A2

    公开(公告)日:2010-06-03

    申请号:PCT/US2009/063023

    申请日:2009-11-03

    CPC classification number: G06K9/6219 G06Q30/02 G06Q30/0205

    Abstract: Method for determining similarities between a first user and a second user in a network, including receiving one or more Global Positioning System (GPS) logs from each user in the network, constructing a first hierarchal graph for the first user's GPS log and a second hierarchical graph for the second user's GPS log, and calculating a similarity score between the first user and the second user based on the first hierarchal graph and the second hierarchical graph.

    Abstract translation: 用于确定网络中的第一用户和第二用户之间的相似性的方法,包括从所述网络中的每个用户接收一个或多个全球定位系统(GPS)日志,为所述第一用户的所述GPS日志构建第一分层图,以及第二分层 用于第二用户的GPS日志的图形,以及基于第一层次图和第二层次图来计算第一用户和第二用户之间的相似性得分。

    METHOD FOR THE EFFORT-OPTIMIZED DETERMINATION OF CLUSTERS IN SENSOR DATA BY MEANS OF AN EMBEDDED SYSTEM
    9.
    发明申请
    METHOD FOR THE EFFORT-OPTIMIZED DETERMINATION OF CLUSTERS IN SENSOR DATA BY MEANS OF AN EMBEDDED SYSTEM 审中-公开
    方法集群的传感器数据中借助嵌入式系统的努力优化测定

    公开(公告)号:WO2009076935A3

    公开(公告)日:2009-10-29

    申请号:PCT/DE2008002065

    申请日:2008-12-12

    CPC classification number: G01S13/931 G01S7/292 G01S7/295 G01S13/524 G06K9/6219

    Abstract: In a method for the determination of clusters (8a, 8b, 8c, 9a, 9b, 9c) in sensor data by means of an embedded system, the formation of the clusters (8a, 8b, 8c, 9a, 9b, 9c) is carried out sequentially in order to reduce the consumption of resources, wherein the clusters (8a, 8b, 8c, 9a, 9b, 9c) formed are modified as a function a further property space dimension when forming new clusters (8a, 8b, 8c, 9a, 9b, 9c).

    Abstract translation: 在用于确定集群的方法(8A,8B,8C,9A,9B,9C)由嵌入式系统的装置中的传感器数据是减少形成簇群的资源消耗(8A,8B,8C,9A,9B,9C)依次进行 其中,所述集群的新的集群形成过程中形成(8A,8B,8C)(9A,9B,9C)可以响应于进一步的特征空间的维数来改变。

    DATA CLUSTERING METHODS AND APPLICATIONS
    10.
    发明申请
    DATA CLUSTERING METHODS AND APPLICATIONS 审中-公开
    数据聚类方法和应用

    公开(公告)号:WO0225574A3

    公开(公告)日:2002-08-22

    申请号:PCT/GB0104236

    申请日:2001-09-24

    CPC classification number: G06F17/30017 G06F17/30247 G06K9/6219

    Abstract: A data clustering method involves techniques for improving the speed of generation of clustering data representing hierarchical clustering of a set of data samples. The techniques include the selection of clusters in increasing size for selecting the nearest other cluster for merging, ordering the data samples according to absolute distance from a reference and searching for nearest neighbours within a restricted index range, and making distance comparisons by summing the contributions from components in each dimension in turn in order of the interquartile ranges of components of the data samples in each dimension. A data classification method involves calculating a rank value for a test sample in relation to a cluster of data samples, by taking into account the dissimilarities of the data samples at either end of the closest edge to the data sample and/or by calculating as a function of a test sample dissimilarity of the test sample to the most similar data sample within the cluster, unless the test sample dissimilarity is less than the dissimilarity of an edge in a minimum spanning tree which has the greatest dissimilarity less than an edge connected to the most similar data sample. The applications of the methods include data compression, feature extraction, unmixing, data mining and browsing, network design and pattern recognition.

    Abstract translation: 数据聚类方法涉及用于提高表示一组数据样本的分层聚类的聚类数据的生成速度的技术。 这些技术包括选择用于合并的最近的其他聚类来选择最近的其他聚类的聚类,根据与参考的绝对距离对数据样本进行排序,并搜索限制指数范围内的最近邻居,并通过将来自 每个维度中的组件依次按照每个维度中数据样本的组件间的四分位数范围。 数据分类方法包括通过考虑在数据样本的最近边缘的任一端处的数据样本的不相似度和/或通过计算作为一个数据样本来计算与数据样本群相关的测试样本的秩值 测试样本与样本集中最相似的数据样本的不相似性的函数,除非测试样本的不相似性小于最小生成树中边缘的差异性, 最相似的数据样本。 这些方法的应用包括数据压缩,特征提取,解混,数据挖掘和浏览,网络设计和模式识别。

Patent Agency Ranking