Method of generating user profile based on user preference and multimedia data browsing system using the same
    61.
    发明授权
    Method of generating user profile based on user preference and multimedia data browsing system using the same 有权
    基于用户偏好生成用户配置文件的方法和使用该配置文件的多媒体数据浏览系统

    公开(公告)号:US07403968B2

    公开(公告)日:2008-07-22

    申请号:US11057764

    申请日:2005-02-15

    IPC分类号: G06F15/16

    摘要: The present invention relates to a method for generating a user profile in indexing/browsing of multimedia data and a multimedia browsing method using the same. The multimedia data browsing method is characterized in that: (a) constructing a user profile by incorporating a user-preferred application description scheme indicating a user-preferred multimedia browsing method or browsing criterion, wherein the browsing method or browsing criterion is described in different way according to a type of the multimedia data in terms of genre; (b) analyzing the user-preferred application description scheme and selecting a relevant application for implementing a user-preferred browsing; and (c) browsing corresponding multimedia data using the selected preferred application.

    摘要翻译: 本发明涉及一种用于在多媒体数据的索引/浏览中生成用户简档的方法和使用其的多媒体浏览方法。 多媒体数据浏览方法的特征在于:(a)通过结合表示用户偏好的多媒体浏览方法或浏览标准的用户优选应用描述方案来构建用户简档,其中以不同的方式描述浏览方法或浏览标准 根据类型的多媒体数据类型; (b)分析用户优选的应用描述方案并选择用于实现用户偏好浏览的相关应用; 和(c)使用所选择的优选应用浏览对应的多媒体数据。

    User profile information data structure based on user preference and multimedia data browsing system using the same
    63.
    发明授权
    User profile information data structure based on user preference and multimedia data browsing system using the same 有权
    用户简档信息数据结构基于用户偏好和多媒体数据浏览系统使用相同

    公开(公告)号:US07318104B1

    公开(公告)日:2008-01-08

    申请号:US09667072

    申请日:2000-09-21

    IPC分类号: G06F15/16

    摘要: The present invention relates to an user profile information data structure for browsing of multimedia data and a multimedia browsing method using the same.The multimedia data browsing method is characterized in that: (a) multimedia data contains a contents description scheme for indexing/browsing based on contents; (b) an user profile includes an user preference description scheme indicating an user-preferred multimedia browsing method or browsing criterion; and (c) multimedia data is browsed by analyzing the user-preferred application description scheme for user-preferred browsing in a corresponding user profile, if the user desires multimedia browsing.

    摘要翻译: 本发明涉及用于浏览多媒体数据的用户简档信息数据结构和使用其的多媒体浏览方法。 多媒体数据浏览方法的特征在于:(a)多媒体数据包含基于内容进行索引/浏览的内容描述方案; (b)用户简档包括指示用户偏好的多媒体浏览方法或浏览标准的用户偏好描述方案; 以及(c)如果用户期望多媒体浏览,则通过分析用户优选的应用描述方案来浏览多媒体数据,以便在相应的用户简档中进行用户首选的浏览。

    Method for extracting object region
    64.
    发明授权
    Method for extracting object region 失效
    提取对象区域的方法

    公开(公告)号:US07313254B2

    公开(公告)日:2007-12-25

    申请号:US10255680

    申请日:2002-09-27

    IPC分类号: G06K9/00

    摘要: The present invention discloses a method for extracting an object region in a motion picture, which can extract the object region of a current frame using different methods based on a degree of motion of the object. Especially, when the object has many motions, an object region of a previous frame is modified by comparing a CDI (Change Detected Image) generated based on a difference between the previous frame and the current frame with the previous frame. As a result, the present invention can be applied to image communication requiring real-time processing, and also applied to techniques requiring precise background change by dividing the object region in pixel units.

    摘要翻译: 本发明公开了一种用于提取运动图像中的对象区域的方法,其可以基于对象的运动程度使用不同的方法来提取当前帧的对象区域。 特别地,当对象具有许多动作时,通过将基于前一帧和当前帧之间的差异生成的CDI(改变检测图像)与前一帧进行比较来修改前一帧的对象区域。 结果,本发明可以应用于需要实时处理的图像通信,并且还应用于通过以像素单位划分对象区域来需要精确的背景改变的技术。

    Method of extracting face using color distortion information

    公开(公告)号:US07133552B2

    公开(公告)日:2006-11-07

    申请号:US09982258

    申请日:2001-10-19

    IPC分类号: G06K9/00

    摘要: Disclosed is a face extraction method using color distortion information. The face extraction method includes extracting color distortion information from the given image, determining a skin color range in a color space using the extracted color distortion information, and performing the face extraction by extracting the skin color region using the determined skin color range. According to the method, the face is more accurately extracted by extracting the color distortion information of a still image or moving image when the image is given, and variably and automatically determining the skin color range suitable for the given image using the color distortion information.

    Method of detecting a specific object in an image signal
    66.
    发明授权
    Method of detecting a specific object in an image signal 失效
    检测图像信号中特定物体的方法

    公开(公告)号:US07085402B2

    公开(公告)日:2006-08-01

    申请号:US10655311

    申请日:2003-09-05

    IPC分类号: G06K9/00

    CPC分类号: G06K9/00228

    摘要: A method of detecting a specific object in an image signal both efficiently and accurately is disclosed. According to the method, an object is first detected from an image or frame using a general feature of the object and in the following image or frame, the object is detected using an object-dependant feature. Also, when detecting a plurality of objects or portions of the object, a full color range of the specific object is determined, and color range sections of the full color range is used to detect the object.

    摘要翻译: 公开了一种高效准确地检测图像信号中特定对象的方法。 根据该方法,首先使用对象的一般特征从图像或帧中检测对象,并且在随后的图像或帧中,使用对象依赖特征来检测对象。 此外,当检测到对象的多个对象或部分时,确定特定对象的全色范围,并且使用全色范围的颜色范围部分来检测对象。

    Method for automatically extracting image effect color and recovering original image color

    公开(公告)号:US06816289B1

    公开(公告)日:2004-11-09

    申请号:US09496956

    申请日:2000-02-03

    IPC分类号: H04N146

    摘要: The present invention relates to an effect color extracting method of an image and an image original color recovering method which are capable of automatically extracting an effect color of an image pictured in accordance with an environment of a certain illumination and a color lens (or filter) and a feature of a camera, adjusting the extracted effect color and recovering an original image color of the image for thereby enhancing a performance of an image search. In the method for recovering an image color pictured based on a certain effect of an original color or other colors or an effect color in accordance with a feature of a camera and a surrounding environment of an object, an image color recovering method includes the steps of comparing all pixels of a frame of the image and a first critical value, obtaining an average hue value Hue_Ave with respect to the hues of the pixels each having a crominance smaller than the first critical value, computing a hue corresponding to the average hue value Hue_Ave, and determining the computed hue as an effect color, and compensating the image color affected by the effect color using the computed hue and adjusting the image color to an original color.

    Method of searching or browsing multimedia data and data structure
    70.
    发明授权
    Method of searching or browsing multimedia data and data structure 有权
    搜索或浏览多媒体数据和数据结构的方法

    公开(公告)号:US06643643B1

    公开(公告)日:2003-11-04

    申请号:US09493038

    申请日:2000-01-28

    IPC分类号: G06F1730

    摘要: A method of searching or browsing multimedia data which can effectively search or browse an image is disclosed. In the present method, the searching or browsing is performed in consideration of at least one of a reliability information on a weight of a feature of an input multimedia data and an authority code. According to the method, the system selects reference multimedia data, and searches the multimedia data using a weight of a feature and/or a feature element of the input multimedia data. A user gives feedback on the relevance of the searched or browsed multimedia data, and the system calculates a new weight using the relevance information. Thus, the system updates and maintains new weights of features and/or feature elements.

    摘要翻译: 公开了一种搜索或浏览可以有​​效地搜索或浏览图像的多媒体数据的方法。 在本方法中,考虑到关于输入多媒体数据的特征的权重和权限代码的可靠性信息中的至少一个来执行搜索或浏览。 根据该方法,系统选择参考多媒体数据,并使用输入多媒体数据的特征和/或特征元素的权重来搜索多媒体数据。 用户对所搜索或浏览的多媒体数据的相关性给出反馈,并且系统使用相关性信息来计算新的权重。 因此,系统更新并维护特征和/或特征元素的新权重。