METHOD AND APPARATUS FOR CLASSIFYING MULTIMEDIA ARTIFACTS USING ONTOLOGY SELECTION AND SEMANTIC CLASSIFICATION
    1.
    发明申请
    METHOD AND APPARATUS FOR CLASSIFYING MULTIMEDIA ARTIFACTS USING ONTOLOGY SELECTION AND SEMANTIC CLASSIFICATION 审中-公开
    使用本体选择和语义分类来分类多媒体伪影的方法和设备

    公开(公告)号:WO2008086032A3

    公开(公告)日:2008-08-21

    申请号:PCT/US2008000364

    申请日:2008-01-10

    Applicant: IBM

    CPC classification number: G06F17/30707 G06F17/30038 Y10S707/99944

    Abstract: A method and apparatus is provided for automatically classifying a multimedia artifact (204) based on scoring, and selecting the appropriate set of ontologies from among all possible sets of ontologies (206), preferably using a recursive routing selection technique (202). The semantic tagging of the multimedia artifact (204) is enhanced by applying only classifiers (208) from the selected ontology (206), for use in classifying the multimedia artifact (204), wherein the classifiers are selected based on the context of the multimedia artifact (204). One embodiment of the invention, directed to a method for classifying a multimedia artifact (204), uses a specified criteria to select one or more ontologies (206), wherein the specified criteria indicates the comparative similarity between specified characteristics of the multimedia artifact (204) and each ontology (206). The method further comprises scoring and selecting one or more classifiers (208) from a plurality of classifiers (208) that respectively correspond to semantic element of the selected ontologies (206), and evaluating the multimedia artifact (204) using the selected classifiers (208) to determine a classification for the multimedia artifact (204).

    Abstract translation: 提供了一种方法和装置,用于基于评分自动分类多媒体人工产物(204),并且优选地使用递归路由选择技术(202)从所有可能的本体集合(206)中选择适当的本体集合。 通过仅应用来自所选本体(206)的分类器(208)来增强多媒体伪像(204)的语义标签以用于分类多媒体伪像(204),其中基于多媒体的上下文来选择分类器 神器(204)。 涉及用于分类多媒体人工产物(204)的方法的本发明的一个实施例使用指定的标准来选择一个或多个本体论(206),其中指定的标准指示多媒体人工产物(204)的指定特征之间的比较相似性 )和每个本体(206)。 该方法进一步包括从分别对应于所选本体(206)的语义元素的多个分类器(208)中评分和选择一个或多个分类器(208),并且使用所选择的分类器(208)评估多媒体工件(204) )来确定多媒体伪像的分类(204)。

    METHOD AND APPARATUS FOR CLASSIFYING MULTIMEDIA ARTIFACTS USING ONTOLOGY SELECTION AND SEMANTIC CLASSIFICATION
    2.
    发明申请
    METHOD AND APPARATUS FOR CLASSIFYING MULTIMEDIA ARTIFACTS USING ONTOLOGY SELECTION AND SEMANTIC CLASSIFICATION 审中-公开
    使用本体选择和语义分类分类多媒体手段的方法和装置

    公开(公告)号:WO2008086032A2

    公开(公告)日:2008-07-17

    申请号:PCT/US2008000364

    申请日:2008-01-10

    Applicant: IBM

    CPC classification number: G06F17/30707 G06F17/30038 Y10S707/99944

    Abstract: A method and apparatus is provided for automatically classifying a multimedia artifact (204) based on scoring, and selecting the appropriate set of ontologies from among all possible sets of ontologies (206), preferably using a recursive routing selection technique (202). The semantic tagging of the multimedia artifact (204) is enhanced by applying only classifiers (208) from the selected ontology (206), for use in classifying the multimedia artifact (204), wherein the classifiers are selected based on the context of the multimedia artifact (204). One embodiment of the invention, directed to a method for classifying a multimedia artifact (204), uses a specified criteria to select one or more ontologies (206), wherein the specified criteria indicates the comparative similarity between specified characteristics of the multimedia artifact (204) and each ontology (206). The method further comprises scoring and selecting one or more classifiers (208) from a plurality of classifiers (208) that respectively correspond to semantic element of the selected ontologies (206), and evaluating the multimedia artifact (204) using the selected classifiers (208) to determine a classification for the multimedia artifact (204).

    Abstract translation: 提供了一种方法和装置,用于基于评分来自动分类多媒体伪影(204),并且优选地使用递归路由选择技术(202)从所有可能的本体集合(206)中选择适当的本体集合。 通过仅从所选择的本体(206)应用分类器(208)来增强多媒体伪像(204)的语义标记,以用于分类多媒体伪像(204),其中基于多媒体的上下文来选择分类器 神器(204)。 本发明的一个实施例涉及用于分类多媒体伪影(204)的方法,使用指定的标准来选择一个或多个本体(206),其中指定的标准表示多媒体伪影(204)的特定特征之间的比较相似度 )和每个本体(206)。 该方法还包括从分别对应于所选本体(206)的语义元素的多个分类器(208)中对一个或多个分类器(208)进行评分和选择,以及使用所选择的分类器(208)评估多媒体伪像(204) )来确定多媒体伪像的分类(204)。

Patent Agency Ranking