IMAGE SIMILARITY FROM DISPARATE SOURCES
    1.
    发明申请
    IMAGE SIMILARITY FROM DISPARATE SOURCES 有权
    来自不同来源的图像相似性

    公开(公告)号:US20110029561A1

    公开(公告)日:2011-02-03

    申请号:US12533475

    申请日:2009-07-31

    IPC分类号: G06F17/30

    摘要: A search engine determines a set of other images that are similar to a user-selected image, and presents those other images to the user. In determining whether two images are sufficiently similar to each other to merit presentation of one, the search engine determines a Euclidean distance between separate feature vectors that are associated with each of the images. Each such vector indicates diverse types of information that is known about the associated image. The types of information included within such a vector may include attributes that reflect visual characteristics that are visible in an image, verbal tags that have been associated with the image users in a community of users, concepts derived from those tags, coordinates that reflect a geographic location at which a camera that produced the image was when the camera produced the image, and concepts related to groups with which the image is associated.

    摘要翻译: 搜索引擎确定与用户选择的图像类似的一组其他图像,并将这些其他图像呈现给用户。 在确定两个图像是否彼此足够相似以表现出一个图像时,搜索引擎确定与每个图像相关联的独立特征向量之间的欧氏距离。 每个这样的向量表示关于相关图像已知的不同类型的信息。 包括在这样的向量内的信息的类型可以包括反映在图像中可见的视觉特征的属性,已经与用户社区中的图像用户相关联的语言标签,从那些标签导出的概念,反映地理的坐标 相机产生图像时产生图像的相机的位置以及与图像相关联的组相关的概念。

    Image similarity from disparate sources
    2.
    发明授权
    Image similarity from disparate sources 有权
    来自不同来源的图像相似性

    公开(公告)号:US09384214B2

    公开(公告)日:2016-07-05

    申请号:US12533475

    申请日:2009-07-31

    IPC分类号: G06F17/30

    摘要: A search engine determines a set of other images that are similar to a user-selected image, and presents those other images to the user. In determining whether two images are sufficiently similar to each other to merit presentation of one, the search engine determines a Euclidean distance between separate feature vectors that are associated with each of the images. Each such vector indicates diverse types of information that is known about the associated image. The types of information included within such a vector may include attributes that reflect visual characteristics that are visible in an image, verbal tags that have been associated with the image users in a community of users, concepts derived from those tags, coordinates that reflect a geographic location at which a camera that produced the image was when the camera produced the image, and concepts related to groups with which the image is associated.

    摘要翻译: 搜索引擎确定与用户选择的图像类似的一组其他图像,并将这些其他图像呈现给用户。 在确定两个图像是否彼此足够相似以表现出一个图像时,搜索引擎确定与每个图像相关联的独立特征向量之间的欧氏距离。 每个这样的向量表示关于相关图像已知的不同类型的信息。 包括在这样的向量内的信息的类型可以包括反映在图像中可见的视觉特征的属性,已经与用户社区中的图像用户相关联的语言标签,从那些标签导出的概念,反映地理的坐标 相机产生图像时产生图像的相机的位置以及与图像相关联的组相关的概念。

    SLIDESHOWS IN SEARCH
    5.
    发明申请
    SLIDESHOWS IN SEARCH 审中-公开
    幻灯片搜索

    公开(公告)号:US20120030013A1

    公开(公告)日:2012-02-02

    申请号:US12844517

    申请日:2010-07-27

    IPC分类号: G06F3/048 G06Q30/00

    CPC分类号: G06Q30/0251 G06F16/954

    摘要: Techniques are provided to allow users to access interested information without performing engaging searches. A content-providing system may track collective interests of a large set of users and/or individual interests of a user. User-selectable items may be presented to the user directly without the user performing searches. Some of the user-selectable items may be associated with slideshows that are, for example, pre-deposited or curated to provide interesting information relating to these user-selectable items. The user may easily access a slideshow and the content therein using easily comprehensible controls presented on a display page.

    摘要翻译: 提供技术以允许用户访问感兴趣的信息,而不执行搜索。 内容提供系统可以跟踪大量用户的集体兴趣和/或用户的个人兴趣。 用户可选择的项目可以直接呈现给用户,而用户不进行搜索。 一些用户可选择的项目可以与例如预先存储或策划的幻灯片相关联,以提供与这些用户可选项目有关的有趣信息。 用户可以使用显示页面上呈现的容易理解的控件来容易地访问幻灯片及其中的内容。