Scheme for extractions and recognitions of telop characters from video data
    7.
    发明授权
    Scheme for extractions and recognitions of telop characters from video data 有权
    从视频数据中提取和识别字幕字符的方案

    公开(公告)号:US06366699B1

    公开(公告)日:2002-04-02

    申请号:US09204957

    申请日:1998-12-03

    IPC分类号: G06K900

    摘要: A scheme for detecting telop character displaying frames in video image which is capable of suppressing erroneous detection of frames without telop characters due to instability of image features is disclosed. In this scheme, each input frame constituting the video data is entered, and whether each input frame is a telop character displaying frame in which telop characters are displayed or not is judged, according to edge pairs detected from each input frame by detecting each two adjacent edge pixels for which intensity gradient directions are opposite on some scanning line used in judging an intensity gradient direction at each edge pixel and for which an intensity difference between said two adjacent edge pixels is within a prescribed range as one edge pair, edge pixels being pixels at which an intensity value locally changes by at least a prescribed amount with respect to a neighboring pixel among a plurality of pixels constituting each input frame.

    摘要翻译: 公开了一种用于检测视频图像中的字幕字符显示帧的方案,其能够抑制由于图像特征的不稳定性而没有字幕字符的帧的错误检测。 在该方案中,输入构成视频数据的每个输入帧,并且根据从每个输入帧检测到的边缘对来判断每个输入帧是否是显示字幕字符的字幕字符显示帧, 边缘像素,其强度梯度方向在用于判断每个边缘像素处的强度梯度方向的一些扫描线上相反,并且所述两个相邻边缘像素之间的强度差在规定范围内作为一个边缘对,边缘像素是像素 其中强度值相对于构成每个输入帧的多个像素中的相邻像素局部地改变至少规定量。

    RECOMMENDATION INFORMATION GENERATION APPARATUS AND RECOMMENDATION INFORMATION GENERATION METHOD
    9.
    发明申请
    RECOMMENDATION INFORMATION GENERATION APPARATUS AND RECOMMENDATION INFORMATION GENERATION METHOD 有权
    推荐信息生成装置和建议信息生成方法

    公开(公告)号:US20110093476A1

    公开(公告)日:2011-04-21

    申请号:US12936758

    申请日:2009-04-02

    IPC分类号: G06F17/30

    CPC分类号: G06F17/30867

    摘要: A recommendation information generation apparatus and a recommendation information generation method that can select a similar user appropriately even if the amount of history information is small. In an information distribution server, a user characteristic vector calculation unit calculates a user characteristic vector of each of users, and a similar user calculation unit calculates the degree of similarity between the users based on the calculated user characteristic vector of each of the users. The similar user calculation unit then selects a similar user who is similar to a first user based on the calculated degree of similarity. A relevance evaluation unit generates recommendation information for the first user based on the characteristic vector of the selected similar user.

    摘要翻译: 即使历史信息量少的情况,也能够适当地选择类似的用户的推荐信息生成装置和推荐信息生成方法。 在信息分发服务器中,用户特征向量计算单元计算每个用户的用户特征向量,并且类似的用户计算单元基于所计算的每个用户的用户特征向量来计算用户之间的相似度。 类似用户计算单元然后基于所计算的相似程度来选择类似于第一用户的类似用户。 相关性评估单元基于所选择的类似用户的特征向量生成第一用户的推荐信息。

    Service recommendation system and service recommendation method
    10.
    发明申请
    Service recommendation system and service recommendation method 有权
    服务推荐系统和服务推荐方法

    公开(公告)号:US20070150300A1

    公开(公告)日:2007-06-28

    申请号:US11643808

    申请日:2006-12-22

    IPC分类号: G06Q99/00

    摘要: A service recommendation system and a service recommendation method capable of improving the probability of the estimation of a user task and recommending a service depending on a user task can be provided. The user role obtaining unit 210 of the service recommendation server 100 obtains the role of a user, and the task estimating unit 207 estimates a user task from a task model associated with the obtained user role and stored in the task knowledge DB 103. The service knowledge retrieving unit 208 retrieves a service capable of assisting a user task obtained from the task estimating unit 207.

    摘要翻译: 可以提供能够提高用户任务的估计概率并根据用户任务推荐服务的服务推荐系统和服务推荐方法。 服务推荐服务器100的用户角色获取单元210获得用户的角色,并且任务估计单元207从与所获取的用户角色相关联并且存储在任务知识DB 103中的任务模型中估计用户任务。 服务知识检索单元208检索能够辅助从任务估计单元207获得的用户任务的服务。