OBJECT IDENTIFICATION IN DIGITAL IMAGES

    公开(公告)号:US20210049768A1

    公开(公告)日:2021-02-18

    申请号:US17086108

    申请日:2020-10-30

    Applicant: eBay Inc.

    Abstract: In an example, a digital image comprising a representation of multiple physical objects is received at a client computer. The digital image is copied into a temporary canvas. The digital image is then analyzed to identify a plurality of potential object areas, each of the potential object areas having pixels with colors similar to the other pixels within the potential object area. A minimum bounding region for each of the identified potential object areas is identified, the minimum bounding region being a smallest region of a particular shape that bounds the corresponding potential object area. The pixels within a selected minimum bounding region are cropped from the digital image. The pixels within the selected minimum bounding region are then sent to an object recognition service on a server to identify an object represented by the pixels within the selected minimum bounding region.

    Object identification in digital images

    公开(公告)号:US11645758B2

    公开(公告)日:2023-05-09

    申请号:US17086108

    申请日:2020-10-30

    Applicant: eBay Inc.

    Abstract: In an example, a digital image comprising a representation of multiple physical objects is received at a client computer. The digital image is copied into a temporary canvas. The digital image is then analyzed to identify a plurality of potential object areas, each of the potential object areas having pixels with colors similar to the other pixels within the potential object area. A minimum bounding region for each of the identified potential object areas is identified, the minimum bounding region being a smallest region of a particular shape that bounds the corresponding potential object area. The pixels within a selected minimum bounding region are cropped from the digital image. The pixels within the selected minimum bounding region are then sent to an object recognition service on a server to identify an object represented by the pixels within the selected minimum bounding region.

    SYSTEMS AND METHODS TO PRESENT IMAGES REPRESENTATIVE OF SEARCHED ITEMS
    3.
    发明申请
    SYSTEMS AND METHODS TO PRESENT IMAGES REPRESENTATIVE OF SEARCHED ITEMS 审中-公开
    系统和方法来呈现图像的搜索项目的代表

    公开(公告)号:US20150169607A1

    公开(公告)日:2015-06-18

    申请号:US14108550

    申请日:2013-12-17

    Applicant: eBay Inc.

    CPC classification number: G06F16/90328

    Abstract: A request that identifies a plurality of items may be received from a device operated by a user. A plurality of view item pages may be accessed. The plurality of view item pages may be accessed based on the plurality of items that were identified in the request. An interface that includes a plurality of images respectively representative of the plurality of items may be generated. The generation of the interface may utilize the accessed plurality of view item pages that correspond to the plurality of items that were identified in the request. Lastly, the interface that includes the plurality of images representative of the plurality of items may be presented to the device operated by the user.

    Abstract translation: 可以从用户操作的设备接收标识多个项目的请求。 可以访问多个查看项目页面。 可以基于在请求中识别的多个项目来访问多个视图项目页面。 可以生成包括分别表示多个项目的多个图像的界面。 接口的生成可以利用对应于在请求中识别的多个项目的访问的多个查看项目页面。 最后,可以将表示多个项目的多个图像的界面呈现给用户操作的设备。

    Object identification in digital images

    公开(公告)号:US11995843B2

    公开(公告)日:2024-05-28

    申请号:US18129494

    申请日:2023-03-31

    Applicant: eBay Inc.

    Abstract: In an example, a digital image comprising a representation of multiple physical objects is received at a client computer. The digital image is copied into a temporary canvas. The digital image is then analyzed to identify a plurality of potential object areas, each of the potential object areas having pixels with colors similar to the other pixels within the potential object area. A minimum bounding region for each of the identified potential object areas is identified, the minimum bounding region being a smallest region of a particular shape that bounds the corresponding potential object area. The pixels within a selected minimum bounding region are cropped from the digital image. The pixels within the selected minimum bounding region are then sent to an object recognition service on a server to identify an object represented by the pixels within the selected minimum bounding region.

    OBJECT IDENTIFICATION IN DIGITAL IMAGES
    6.
    发明公开

    公开(公告)号:US20230237670A1

    公开(公告)日:2023-07-27

    申请号:US18129494

    申请日:2023-03-31

    Applicant: eBay Inc.

    Abstract: In an example, a digital image comprising a representation of multiple physical objects is received at a client computer. The digital image is copied into a temporary canvas. The digital image is then analyzed to identify a plurality of potential object areas, each of the potential object areas having pixels with colors similar to the other pixels within the potential object area. A minimum bounding region for each of the identified potential object areas is identified, the minimum bounding region being a smallest region of a particular shape that bounds the corresponding potential object area. The pixels within a selected minimum bounding region are cropped from the digital image. The pixels within the selected minimum bounding region are then sent to an object recognition service on a server to identify an object represented by the pixels within the selected minimum bounding region.

    Object identification in digital images

    公开(公告)号:US10861162B2

    公开(公告)日:2020-12-08

    申请号:US15836202

    申请日:2017-12-08

    Applicant: eBay Inc.

    Abstract: In an example, a digital image comprising a representation of multiple physical objects is received at a client computer. The digital image is copied into a temporary canvas. The digital image is then analyzed to identify a plurality of potential object areas, each of the potential object areas having pixels with colors similar to the other pixels within the potential object area. A minimum bounding region for each of the identified potential object areas is identified, the minimum bounding region being a smallest region of a particular shape that bounds the corresponding potential object area. The pixels within a selected minimum bounding region are cropped from the digital image. The pixels within the selected minimum bounding region are then sent to an object recognition service on a server to identify an object represented by the pixels within the selected minimum bounding region.

    OBJECT IDENTIFICATION IN DIGITAL IMAGES
    8.
    发明申请

    公开(公告)号:US20190180446A1

    公开(公告)日:2019-06-13

    申请号:US15836202

    申请日:2017-12-08

    Applicant: eBay Inc.

    Abstract: In an example, a digital image comprising a representation of multiple physical objects is received at a client computer. The digital image is copied into a temporary canvas. The digital image is then analyzed to identify a plurality of potential object areas, each of the potential object areas having pixels with colors similar to the other pixels within the potential object area. A minimum bounding region for each of the identified potential object areas is identified, the minimum bounding region being a smallest region of a particular shape that bounds the corresponding potential object area. The pixels within a selected minimum bounding region are cropped from the digital image. The pixels within the selected minimum bounding region are then sent to an object recognition service on a server to identify an object represented by the pixels within the selected minimum bounding region.

Patent Agency Ranking