SCALABLE NEAR DUPLICATE IMAGE SEARCH WITH GEOMETRIC CONSTRAINTS
    1.
    发明申请
    SCALABLE NEAR DUPLICATE IMAGE SEARCH WITH GEOMETRIC CONSTRAINTS 有权
    可近似的几何图像搜索与几何约束

    公开(公告)号:US20120314961A1

    公开(公告)日:2012-12-13

    申请号:US13595345

    申请日:2012-08-27

    IPC分类号: G06K9/46

    摘要: Methods are disclosed for finding images from a large corpus of images that at least partially match a query image. The present method makes use of feature detectors to bundle features into local groups or bundles. These bundled features are repeatable and much more discriminative than an individual SIFT feature. Equally importantly, the bundled features provide a flexible representation that allows simple and robust geometric constraints to be efficiently enforced when querying the index.

    摘要翻译: 公开了用于从至少部分匹配查询图像的大图像的图像中发现图像的方法。 本方法利用特征检测器将特征分组到本地组或束中。 这些捆绑功能是可重复的,比单独的SIFT功能更具歧视性。 同样重要的是,捆绑功能提供了灵活的表示,允许在查询索引时有效执行简单和强大的几何约束。

    Scalable near duplicate image search with geometric constraints
    2.
    发明授权
    Scalable near duplicate image search with geometric constraints 有权
    可扩展的几何重复图像搜索与几何约束

    公开(公告)号:US08787680B2

    公开(公告)日:2014-07-22

    申请号:US13595345

    申请日:2012-08-27

    IPC分类号: G06K9/46 G06K9/54

    摘要: Methods are disclosed for finding images from a large corpus of images that at least partially match a query image. The present method makes use of feature detectors to bundle features into local groups or bundles. These bundled features are repeatable and much more discriminative than an individual SIFT feature. Equally importantly, the bundled features provide a flexible representation that allows simple and robust geometric constraints to be efficiently enforced when querying the index.

    摘要翻译: 公开了用于从至少部分匹配查询图像的大图像的图像中发现图像的方法。 本方法利用特征检测器将特征分组到本地组或束中。 这些捆绑功能是可重复的,比单独的SIFT功能更具歧视性。 同样重要的是,捆绑功能提供了灵活的表示,允许在查询索引时有效执行简单和强大的几何约束。

    SCALABLE NEAR DUPLICATE IMAGE SEARCH WITH GEOMETRIC CONSTRAINTS
    3.
    发明申请
    SCALABLE NEAR DUPLICATE IMAGE SEARCH WITH GEOMETRIC CONSTRAINTS 有权
    可近似的几何图像搜索与几何约束

    公开(公告)号:US20100195914A1

    公开(公告)日:2010-08-05

    申请号:US12364090

    申请日:2009-02-02

    IPC分类号: G06F17/30 G06K9/46

    摘要: Methods are disclosed for finding images from a large corpus of images that at least partially match a query image. The present method makes use of feature detectors to bundle features into local groups or bundles. These bundled features are repeatable and much more discriminative than an individual SIFT feature. Equally importantly, the bundled features provide a flexible representation that allows simple and robust geometric constraints to be efficiently enforced when querying the index.

    摘要翻译: 公开了用于从至少部分匹配查询图像的大图像的图像中发现图像的方法。 本方法利用特征检测器将特征分组到本地组或束中。 这些捆绑功能是可重复的,比单独的SIFT功能更具歧视性。 同样重要的是,捆绑功能提供了灵活的表示,允许在查询索引时有效执行简单和强大的几何约束。

    Scalable near duplicate image search with geometric constraints
    4.
    发明授权
    Scalable near duplicate image search with geometric constraints 有权
    可扩展的几何重复图像搜索与几何约束

    公开(公告)号:US08254697B2

    公开(公告)日:2012-08-28

    申请号:US12364090

    申请日:2009-02-02

    IPC分类号: G06K9/46 G06K9/54

    摘要: Methods are disclosed for finding images from a large corpus of images that at least partially match a query image. The present method makes use of feature detectors to bundle features into local groups or bundles. These bundled features are repeatable and much more discriminative than an individual SIFT feature. Equally importantly, the bundled features provide a flexible representation that allows simple and robust geometric constraints to be efficiently enforced when querying the index.

    摘要翻译: 公开了用于从至少部分匹配查询图像的大图像的图像中发现图像的方法。 本方法利用特征检测器将特征分组到本地组或束中。 这些捆绑功能是可重复的,比单独的SIFT功能更具歧视性。 同样重要的是,捆绑功能提供了灵活的表示,允许在查询索引时有效执行简单和强大的几何约束。

    Scalable face image retrieval
    5.
    发明授权
    Scalable face image retrieval 有权
    可扩展的面部图像检索

    公开(公告)号:US08498455B2

    公开(公告)日:2013-07-30

    申请号:US12792750

    申请日:2010-06-03

    IPC分类号: G06K9/00

    CPC分类号: G06K9/4676 G06K9/00281

    摘要: A system for identifying individuals in digital images and for providing matching digital images is provided. A set of images that include faces of known individuals is received. Faces are detected in the images and facial components are identified in each face. Visual words corresponding to the facial components are generated, stored, and associated with identifiers of the individuals. At a later time, a user may provide an image that includes the face of one of the known individuals. Visual words are determined from the face of the individual in the provided image and matched against the stored visual words. Images associated with matching visual words are ranked and presented to the user.

    摘要翻译: 提供了一种用于识别数字图像中的个体并提供匹配的数字图像的系统。 接收包括已知个人面孔的一组图像。 在图像中检测到面部,并且在每个面部中识别面部组件。 对应于面部组件的视觉词被生成,存储并与个人的标识符相关联。 在稍后的时间,用户可以提供包括已知个体之一的脸部的图像。 视觉词是从提供的图像中的个体的脸部确定的,并且与存储的视觉词匹配。 与匹配的视觉词相关联的图像被排序并呈现给用户。

    SCALABLE FACE IMAGE RETRIEVAL
    6.
    发明申请
    SCALABLE FACE IMAGE RETRIEVAL 有权
    可扩展的脸部图像检索

    公开(公告)号:US20110299743A1

    公开(公告)日:2011-12-08

    申请号:US12792750

    申请日:2010-06-03

    IPC分类号: G06T7/00

    CPC分类号: G06K9/4676 G06K9/00281

    摘要: A system for identifying individuals in digital images and for providing matching digital images is provided. A set of images that include faces of known individuals is received. Faces are detected in the images and facial components are identified in each face. Visual words corresponding to the facial components are generated, stored, and associated with identifiers of the individuals. At a later time, a user may provide an image that includes the face of one of the known individuals. Visual words are determined from the face of the individual in the provided image and matched against the stored visual words. Images associated with matching visual words are ranked and presented to the user.

    摘要翻译: 提供了一种用于识别数字图像中的个体并提供匹配的数字图像的系统。 接收包括已知个人面孔的一组图像。 在图像中检测到面部,并且在每个面部中识别面部组件。 对应于面部组件的视觉词被生成,存储并与个人的标识符相关联。 在稍后的时间,用户可以提供包括已知个体之一的脸部的图像。 视觉词是从提供的图像中的个体的脸部确定的,并且与存储的视觉词匹配。 与匹配视觉词相关联的图像被排序并呈现给用户。

    Multi-layer stack adjacent to granular layer
    7.
    发明授权
    Multi-layer stack adjacent to granular layer 有权
    多层堆叠与颗粒层相邻

    公开(公告)号:US08404368B2

    公开(公告)日:2013-03-26

    申请号:US12847768

    申请日:2010-07-30

    IPC分类号: G11B5/66 G11B5/667 G11B5/673

    CPC分类号: G11B5/82 G11B5/65 G11B5/66

    摘要: In some embodiments, an article comprising a first magnetic recording layer, the first magnetic recording layer including a granular layer having a first magnetic anisotropy and a multi-layer stack adjacent the granular layer, the multi-layer stack comprising one or more substantially magnetic film layers alternating with one or more polarization conductor layers, wherein the multi-layer stack has a second magnetic anisotropy that is greater than the first magnetic anisotropy.

    摘要翻译: 在一些实施例中,一种包括第一磁记录层的物品,第一磁记录层包括具有第一磁各向异性的颗粒层和与颗粒层相邻的多层堆叠,所述多层堆叠包括一个或多个基本磁性膜 层与一个或多个极化导体层交替,其中多层堆叠具有大于第一磁各向异性的第二磁各向异性。

    MULTI-LAYER STACK ADJACENT TO GRANULAR LAYER
    8.
    发明申请
    MULTI-LAYER STACK ADJACENT TO GRANULAR LAYER 有权
    多层堆叠与颗粒层相邻

    公开(公告)号:US20120026627A1

    公开(公告)日:2012-02-02

    申请号:US12847768

    申请日:2010-07-30

    IPC分类号: G11B5/82 B05D5/12

    CPC分类号: G11B5/82 G11B5/65 G11B5/66

    摘要: In some embodiments, an article comprising a first magnetic recording layer, the first magnetic recording layer including a granular layer having a first magnetic anisotropy and a multi-layer stack adjacent the granular layer, the multi-layer stack comprising one or more substantially magnetic film layers alternating with one or more polarization conductor layers, wherein the multi-layer stack has a second magnetic anisotropy that is greater than the first magnetic anisotropy.

    摘要翻译: 在一些实施例中,一种包括第一磁记录层的物品,第一磁记录层包括具有第一磁各向异性的颗粒层和与颗粒层相邻的多层堆叠,所述多层堆叠包括一个或多个基本磁性膜 层与一个或多个极化导体层交替,其中所述多层堆叠具有大于所述第一磁各向异性的第二磁各向异性。

    Substantially two dimensional isotropic magnetic recording medium
comprising a NiAl underlayer
    10.
    发明授权
    Substantially two dimensional isotropic magnetic recording medium comprising a NiAl underlayer 有权
    基本二维各向同性磁记录介质,其包括NiAl底层

    公开(公告)号:US6110582A

    公开(公告)日:2000-08-29

    申请号:US149096

    申请日:1998-09-08

    IPC分类号: G11B5/73 G11B5/84 G11B5/66

    摘要: A high areal density magnetic recording medium exhibiting high H.sub.c, high SNR, high S* and substantially two dimensionally isotropic magnetic properties is achieved by depositing a NiAl underlayer on a NiP-plated non-magnetic metallic substrate, such as an Al alloy substrate. Embodiments include depositing a Cr layer on the NiAl underlayer. The NiAl underlayer and/or Cr layer can optionally contain an alloying element for inducing a preferred HCP crystallographic structure in the magnetic layer by lattice matching.

    摘要翻译: 通过在诸如Al合金基底的NiP镀非磁性金属基底上沉积NiAl底层,实现了表现出高Hc,高SNR,高S *和基本二维各向同性磁性能的高密度磁记录介质。 实施例包括在NiAl底层上沉积Cr层。 NiAl底层和/或Cr层可以任选地含有用于通过晶格匹配在磁性层中诱导优选HCP晶体结构的合金元素。