GoF/GoP texture description method, and texture-based GoF/GoP retrieval method and apparatus using the same
    1.
    发明授权
    GoF/GoP texture description method, and texture-based GoF/GoP retrieval method and apparatus using the same 失效
    GoF / GoP纹理描述方法和基于纹理的GoF / GoP检索方法和使用该方法的设备

    公开(公告)号:US07519114B2

    公开(公告)日:2009-04-14

    申请号:US10892463

    申请日:2004-07-16

    申请人: Sang-kyun Kim

    发明人: Sang-kyun Kim

    IPC分类号: H04N7/12 H04N7/18

    CPC分类号: G06F17/30262 G06F17/30808

    摘要: A method of describing texture of a group of frames (GoF) or a group of pictures (GoP) using homogeneous texture descriptors, and a method and apparatus for retrieving a GoF/GoP using the texture description method are provided. The texture description method includes: generating homogeneous texture descriptors of all frames constituting the GoF or all pictures constituting the GoF; and expressing the GoF or GoP using a predetermined representative homogeneous texture descriptor corresponding to one frame or picture to reduce the amount of data. The GoF/GoP retrieval method includes: establishing a database of homogeneous texture descriptors of a plurality of GoFs' or GoPs', each GoF or GoP being expressed by a predetermined representative homogeneous texture descriptor corresponding to one frame or picture to reduce the amount of data; generating a homogeneous texture descriptor corresponding to one frame or picture of a query GoF or GoP when the query GoF or GoP is input; searching homogeneous texture descriptors that are similar to the homogeneous texture descriptor of the query GoF or GoP in the database; and retrieving GoFs' or GoPs' corresponding to the searched similar homogeneous texture descriptors and arranging GoFs' or GoPs' in the order of degree of similarity. Therefore, the texture of images can be more accurately expressed, and an image can be more efficiently and rapidly retrieved.

    摘要翻译: 提供了使用均​​匀纹理描述符来描述一组帧(GoF)或一组图像(GoP)的纹理的方法,以及使用纹理描述方法检索GoF / GoP的方法和装置。 纹理描述方法包括:生成构成GoF的所有帧的均匀纹理描述符或构成GoF的所有图像; 并且使用与一帧或图片相对应的预定代表均匀纹理描述符表示GoF或GoP以减少数据量。 GoF / GoP检索方法包括:建立多个GoFs或GoP的同构纹理描述符的数据库,每个GoF或GoP由对应于一个帧或图片的预定的代表性均匀纹理描述符表示,以减少数据量 ; 当输入查询GoF或GoP时,生成与查询GoF或GoP的一个帧或图片相对应的均匀纹理描述符; 搜索类似于数据库中查询GoF或GoP的均匀纹理描述符的均匀纹理描述符; 并且检索对应于所搜索的相似均质纹理描述符的GoFs或GoP,并按照相似度的顺序排列GoFs或GoP。 因此,可以更准确地表达图像的纹理,并且可以更有效和快速地检索图像。

    Scalably presenting a collection of media objects
    4.
    发明授权
    Scalably presenting a collection of media objects 有权
    可扩展地呈现媒体对象的集合

    公开(公告)号:US07131059B2

    公开(公告)日:2006-10-31

    申请号:US10334769

    申请日:2002-12-31

    申请人: Pere Obrador

    发明人: Pere Obrador

    IPC分类号: G06F15/00

    摘要: Systems and methods of presenting media objects are described. In one aspect, a group of media objects is selected from the collection based upon media object relevance to one or more data structures of a selected media file of indexed, temporally-ordered data structures. One or more of the selected media file and the media objects of the selected group are transmitted to a client for contemporaneous presentation at a selected summarization level. In another aspect, media objects in the collection are grouped into multiple clusters based upon one or more media object relevance criteria. The media object clusters are arranged into a hierarchy of two or more levels. A selected cluster is transmitted to a client for contemporaneous presentation at a selected summarization level.

    摘要翻译: 描述介绍媒体对象的系统和方法。 在一个方面,基于媒体对象与索引的,时间有序的数据结构的所选媒体文件的一个或多个数据结构的相关性,从集合中选择一组媒体对象。 所选择的组的所选择的媒体文件和媒体对象中的一个或多个被发送到客户端以在选择的摘要级别进行同时呈现。 在另一方面,基于一个或多个媒体对象相关性标准将集合中的媒体对象分组成多个集群。 媒体对象集群被布置成两个或多个层次的层次结构。 所选择的集群被发送到客户端以在选定的摘要级别进行同时呈现。

    Pattern discovery in multi-dimensional time series using multi-resolution matching
    5.
    发明授权
    Pattern discovery in multi-dimensional time series using multi-resolution matching 失效
    使用多分辨率匹配的多维时间序列中的模式发现

    公开(公告)号:US07103222B2

    公开(公告)日:2006-09-05

    申请号:US10285928

    申请日:2002-11-01

    申请人: Kadir A. Peker

    发明人: Kadir A. Peker

    IPC分类号: G06K9/00 G06K9/62

    摘要: A method discovers patterns in unknown multi-dimensional data. A time-series of the multi-dimensional data is generated and a point cross-distance matrix is constructed by self-correlating the time-series. All minimum cost paths in the point cross-distance matrix are located at multiple time resolutions. The minimum cost paths are then related to temporal sub-sequences in the multi-dimensional data to discover high-level patterns in the unknown multi-dimensional data.

    摘要翻译: 一种方法发现未知多维数据中的模式。 生成多维数据的时间序列,并通过对时间序列进行自相关构造点交叉距离矩阵。 点交叉距离矩阵中的所有最小成本路径均位于多个时间分辨率。 然后,最小成本路径与多维数据中的时间子序列相关,以发现未知多维数据中的高级模式。

    Image retrieval system and image retrieval method
    7.
    发明授权
    Image retrieval system and image retrieval method 有权
    图像检索系统和图​​像检索方法

    公开(公告)号:US06665442B2

    公开(公告)日:2003-12-16

    申请号:US09773570

    申请日:2001-02-02

    IPC分类号: G06K962

    摘要: When a retrieval condition of an attribute list is input from a user interface unit to a retrieval processing unit, the attribute list stored in an attribute list storing unit is retrieved in the retrieval processing unit. Thereafter, attribute information conforming to the retrieval condition is output to and displayed on a displaying unit. Thereafter, when a retrieval condition of the similarity retrieval is input from the user interface unit to the retrieval processing unit, image data stored in the image information storing unit is retrieved in the retrieval processing unit, and specific image data relating to a characteristic descriptor set conforming to the retrieval condition is selected in the retrieval processing unit. Thereafter, the specific image data is output to and displayed on the displaying unit.

    摘要翻译: 当从用户接口单元向检索处理单元输入属性列表的检索条件时,在检索处理单元中检索存储在属性列表存储单元中的属性列表。 此后,将符合检索条件的属性信息输出并显示在显示单元上。 此后,当从用户接口单元向检索处理单元输入相似性检索的检索条件时,在检索处理单元中检索存储在图像信息存储单元中的图像数据,并且与特征描述符集合有关的特定图像数据 在检索处理单元中选择符合检索条件的信息。 此后,将特定图像数据输出并显示在显示单元上。

    Multimedia event detection and summarization
    9.
    发明授权
    Multimedia event detection and summarization 失效
    多媒体事件检测与总结

    公开(公告)号:US07409407B2

    公开(公告)日:2008-08-05

    申请号:US10840824

    申请日:2004-05-07

    IPC分类号: G06F17/30 G06F17/00

    摘要: A method detects events in multimedia. Features are extracted from the multimedia. The features are sampled using a sliding window to obtain samples. A context model is constructed for each sample. An affinity matrix is determined from the models and a commutative distance metric between each pair of context models. A second generation eigenvector is determined for the affinity matrix, and the samples are then clustered into events according to the second generation eigenvector.

    摘要翻译: 一种方法来检测多媒体中的事件。 功能从多媒体提取。 使用滑动窗口对特征进行采样以获得样品。 为每个样本构建上下文模型。 从模型和每对上下文模型之间的交换距离度量确定亲和度矩阵。 针对亲和度矩阵确定第二代特征向量,然后根据第二代特征向量将样本聚类成事件。

    Method of selecting seeds for the clustering of key-frames
    10.
    发明申请
    Method of selecting seeds for the clustering of key-frames 有权
    选择种子用于聚类关键帧的方法

    公开(公告)号:US20060146199A1

    公开(公告)日:2006-07-06

    申请号:US10532282

    申请日:2003-10-27

    IPC分类号: G06K9/00 H04N5/14 H04N9/64

    摘要: The method is characterized in that it implements the following steps: random drawing of p candidates from the set of key images, calculation of a cost C for each candidate, selection of the candidate minimizing the cost C, determination of a subset from among the set of key images such that the key images forming the said subset have a distance from the candidate less than a threshold T, determination of a seed from among the key images of the subset such that it minimizes the cost function C for this subset, deletion of the key images of the subset to form a new set of key images for at least one new random draw and determination of a new seed according to the previous 5 steps. The field is that of the selection of shots of interest in a video sequence.

    摘要翻译: 该方法的特征在于它实现以下步骤:从该组密钥图像中随机绘制p个候选,计算每个候选的成本C,选择最小化成本C的候选者,确定集合中的子集 的关键图像,使得形成所述子集的关键图像具有距候选者小于阈值T的距离,从子集的关键图像中确定种子,使得其将该子集的成本函数C最小化,删除 该子集的关键图像根据前面的5个步骤形成一组新的关键图像,用于至少一个新的随机抽取和确定新的种子。 该领域是对视频序列中感兴趣的照片的选择。