RELEVANCE FEEDBACK ON A SEGMENT OF A DATA OBJECT
    1.
    发明申请
    RELEVANCE FEEDBACK ON A SEGMENT OF A DATA OBJECT 有权
    数据对象分段的相关反馈

    公开(公告)号:US20110246466A1

    公开(公告)日:2011-10-06

    申请号:US13133662

    申请日:2009-12-18

    IPC分类号: G06F17/30

    CPC分类号: G06F17/30277

    摘要: The invention relates to a method, a system (101) and a computer program product to identify a particular data object of a data type in a database (104) that comprises data objects of the data type. The system (101) comprises a query composition unit (102) to compose a search query to identify a candidate data object being a candidate for the particular data object. A search unit (103) identifies the candidate data object in the database (104) based on the search query. A presentation unit (105) presents the candidate data object to the user. A feedback receiving unit (106) receives user feedback on the relevance or irrelevance of a segment of the candidate data object. The search unit (103) further identifies an improved candidate data object in response to the received user feedback. The improved candidate data object is an improved candidate for the particular data object.

    摘要翻译: 本发明涉及一种方法,系统(101)和计算机程序产品,用于识别包括数据类型的数据对象的数据库(104)中的数据类型的特定数据对象。 系统(101)包括查询合成单元(102),用于组成搜索查询以识别作为特定数据对象候选的候选数据对象。 搜索单元(103)基于搜索查询来识别数据库(104)中的候选数据对象。 呈现单元(105)将候选数据对象呈现给用户。 反馈接收单元(106)接收关于候选数据对象的段的相关性或不相关性的用户反馈。 搜索单元(103)还响应于接收到的用户反馈来识别改进的候选数据对象。 改进的候选数据对象是特定数据对象的改进的候选者。

    VISUALIZATION OF RELEVANCE FOR CONTENT-BASED IMAGE RETRIEVAL
    2.
    发明申请
    VISUALIZATION OF RELEVANCE FOR CONTENT-BASED IMAGE RETRIEVAL 有权
    基于内容的图像检索的可视化

    公开(公告)号:US20120158717A1

    公开(公告)日:2012-06-21

    申请号:US13392113

    申请日:2010-08-30

    IPC分类号: G06F17/30

    摘要: The invention relates to a system (100) for retrieving an image from the storage of images, the system comprising: a retrieval unit (110) for retrieving an image from the storage of images, on the basis of similarity of images from the storage of images o a query image, wherein the similarity is defined by means of a similarity function; a relevance unit (120) for computing images t relevance of a first portion of the retrieved image to a respective first portion of the query image and of a second portion of the retrieved image to a respective second portion of the query image; and a visualization unit (130) for visualizing the relevance of the first and second portion of the retrieved image to the respective first and second portion of the query image. The relevance of the first and second portion of the retrieved image to the respective first and second portion of the query image may be computed using a first and second relevance function. The computed values of the relevance may be visualized, e.g. using a color coding and coloring the first and second portion of each retrieved image. The colored portions are easy to see and analyze. Thus, the system of the invention facilitates visualizing and comparing retrieved images with respect to each other as well as with the query image.

    摘要翻译: 本发明涉及一种用于从图像存储中检索图像的系统(100),该系统包括:检索单元(110),用于根据图像的存储的图像的相似度,从图像的存储中检索图像 图像oa查询图像,其中相似性通过相似度函数来定义; 相关单元(120),用于将所述检索图像的第一部分与所述查询图像的相应第一部分和所述检索图像的第二部分的相关性计算到所述查询图像的相应第二部分; 以及可视化单元(130),用于将检索到的图像的第一和第二部分的相关性可视化到查询图像的相应第一和第二部分。 可以使用第一和第二相关函数来计算检索图像的第一部分和第二部分与查询图像的相应第一和第二部分的相关性。 相关性的计算值可以被可视化,例如。 使用颜色编码和着色每个检索到的图像的第一和第二部分。 彩色部分易于查看和分析。 因此,本发明的系统有助于将检索到的图像相对于彼此以及与查询图像进行可视化和比较。

    Relevance feedback on a segment of a data object

    公开(公告)号:US09720937B2

    公开(公告)日:2017-08-01

    申请号:US13133662

    申请日:2009-12-18

    IPC分类号: G06F7/00 G06F17/30

    CPC分类号: G06F17/30277

    摘要: The invention relates to a method, a system (101) and a computer program product to identify a particular data object of a data type in a database (104) that comprises data objects of the data type. The system (101) comprises a query composition unit (102) to compose a search query to identify a candidate data object being a candidate for the particular data object. A search unit (103) identifies the candidate data object in the database (104) based on the search query. A presentation unit (105) presents the candidate data object to the user. A feedback receiving unit (106) receives user feedback on the relevance or irrelevance of a segment of the candidate data object. The search unit (103) further identifies an improved candidate data object in response to the received user feedback. The improved candidate data object is an improved candidate for the particular data object.

    Visualization of relevance for content-based image retrieval
    4.
    发明授权
    Visualization of relevance for content-based image retrieval 有权
    基于内容的图像检索的可视化

    公开(公告)号:US09495388B2

    公开(公告)日:2016-11-15

    申请号:US13392113

    申请日:2010-08-30

    IPC分类号: G06F17/30 G06F19/00

    摘要: A system (100) includes a retrieval unit (110) for retrieving an image from the storage of images, on the basis of the similarity of images from the storage of images to a query image. The similarity is defined by means of a similarity function. A relevance unit (120) computes the relevance of a first portion of the retrieved image to a respective first portion of the query image and of a second portion of the retrieved image to the respective second portion of the query image. A visualization unit (130) visualizes the relevance of the first and second portion of the retrieved image to the respective first and second portion of the query image. The relevance of the first and second portion of the retrieved image to the respective first and second portion of the query image is computed using a first and second relevance function. The computed values of the relevance are visualized, e.g. using a color coding and coloring the first and second portion of each retrieved image. The colored portions are easy to see and analyze. Thus, the system facilitates visualizing and comparing retrieved images with respect to each other as well as with the query image.

    摘要翻译: 系统(100)包括检索单元(110),用于根据从图像存储到查询图像的图像的相似度,从图像的存储中检索图像。 相似性通过相似度函数来定义。 相关单元(120)将检索到的图像的第一部分与查询图像的相应第一部分和检索到的图像的第二部分的相关性计算到查询图像的相应第二部分。 可视化单元(130)将检索到的图像的第一和第二部分的相关性可视化到查询图像的相应的第一和第二部分。 使用第一和第二相关函数来计算检索图像的第一部分和第二部分与查询图像的相应第一和第二部分的相关性。 相关性的计算值可视化,例如。 使用颜色编码和着色每个检索到的图像的第一和第二部分。 彩色部分易于查看和分析。 因此,该系统便于相对于彼此以及查询图像的检索图像的可视化和比较。