Estimating word correlations from images
    1.
    发明授权
    Estimating word correlations from images 有权
    从图像估计字相关性

    公开(公告)号:US08457416B2

    公开(公告)日:2013-06-04

    申请号:US11956333

    申请日:2007-12-13

    IPC分类号: G06K9/72

    CPC分类号: G06F17/30247 G06F17/30731

    摘要: Word correlations are estimated using a content-based method, which uses visual features of image representations of the words. The image representations of the subject words may be generated by retrieving images from data sources (such as the Internet) using image search with the subject words as query words. One aspect of the techniques is based on calculating the visual distance or visual similarity between the sets of retrieved images corresponding to each query word. The other is based on calculating the visual consistence among the set of the retrieved images corresponding to a conjunctive query word. The combination of the content-based method and a text-based method may produce even better result.

    摘要翻译: 使用基于内容的方法来估计词相关性,其使用词的图像表示的视觉特征。 可以通过使用将主题词作为查询词的图像搜索从数据源(例如因特网)检索图像来生成主题词的图像表示。 该技术的一个方面是基于计算对应于每个查询词的检索图像组之间的视觉距离或视觉相似度。 另一个是基于计算与连接查询词对应的检索到的图像的集合之间的视觉一致性。 基于内容的方法和基于文本的方法的组合可以产生更好的结果。

    Estimating Word Correlations from Images
    2.
    发明申请
    Estimating Word Correlations from Images 有权
    估计图像中的词相关性

    公开(公告)号:US20090074306A1

    公开(公告)日:2009-03-19

    申请号:US11956333

    申请日:2007-12-13

    IPC分类号: G06K9/72

    CPC分类号: G06F17/30247 G06F17/30731

    摘要: Word correlations are estimated using a content-based method, which uses visual features of image representations of the words. The image representations of the subject words may be generated by retrieving images from data sources (such as the Internet) using image search with the subject words as query words. One aspect of the techniques is based on calculating the visual distance or visual similarity between the sets of retrieved images corresponding to each query word. The other is based on calculating the visual consistence among the set of the retrieved images corresponding to a conjunctive query word. The combination of the content-based method and a text-based method may produce even better result.

    摘要翻译: 使用基于内容的方法来估计词相关性,其使用词的图像表示的视觉特征。 可以通过使用将主题词作为查询词的图像搜索从数据源(例如因特网)检索图像来生成主题词的图像表示。 该技术的一个方面是基于计算对应于每个查询词的检索图像组之间的视觉距离或视觉相似度。 另一个是基于计算与连接查询词对应的检索到的图像的集合之间的视觉一致性。 基于内容的方法和基于文本的方法的组合可以产生更好的结果。

    Dual Cross-Media Relevance Model for Image Annotation
    3.
    发明申请
    Dual Cross-Media Relevance Model for Image Annotation 有权
    图像注释的双重跨媒体相关性模型

    公开(公告)号:US20090076800A1

    公开(公告)日:2009-03-19

    申请号:US11956331

    申请日:2007-12-13

    IPC分类号: G06F17/21

    CPC分类号: G06F17/241 G06F17/2735

    摘要: A dual cross-media relevance model (DCMRM) is used for automatic image annotation. In contrast to the traditional relevance models which calculate the joint probability of words and images over a training image database, the DCMRM model estimates the joint probability by calculating the expectation over words in a predefined lexicon. The DCMRM model may be advantageous because a predefined lexicon potentially has better behavior than a training image database. The DCMRM model also takes advantage of content-based techniques and image search techniques to define the word-to-image and word-to-word relations involved in image annotation. Both relations can be estimated by using image search techniques on the web data as well as available training data.

    摘要翻译: 双重跨媒体相关性模型(DCMRM)用于自动图像注释。 与在训练图像数据库中计算单词和图像的联合概率的传统相关性模型相反,DCMRM模型通过计算预定义词典中的单词的期望来估计联合概率。 DCMRM模型可能是有利的,因为预定义词典潜在地具有比训练图像数据库更好的行为。 DCMRM模型还利用基于内容的技术和图像搜索技术来定义图像注释中涉及的单词到图像和单词对字的关系。 可以通过使用图像搜索技术对网络数据以及可用的训练数据来估计这两个关系。

    Dual cross-media relevance model for image annotation
    4.
    发明授权
    Dual cross-media relevance model for image annotation 有权
    用于图像注释的双跨媒体相关性模型

    公开(公告)号:US08571850B2

    公开(公告)日:2013-10-29

    申请号:US11956331

    申请日:2007-12-13

    IPC分类号: G06F17/27

    CPC分类号: G06F17/241 G06F17/2735

    摘要: A dual cross-media relevance model (DCMRM) is used for automatic image annotation. In contrast to the traditional relevance models which calculate the joint probability of words and images over a training image database, the DCMRM model estimates the joint probability by calculating the expectation over words in a predefined lexicon. The DCMRM model may be advantageous because a predefined lexicon potentially has better behavior than a training image database. The DCMRM model also takes advantage of content-based techniques and image search techniques to define the word-to-image and word-to-word relations involved in image annotation. Both relations can be estimated by using image search techniques on the web data as well as available training data.

    摘要翻译: 双重跨媒体相关性模型(DCMRM)用于自动图像注释。 与在训练图像数据库中计算单词和图像的联合概率的传统相关性模型相反,DCMRM模型通过计算预定义词典中的单词的期望来估计联合概率。 DCMRM模型可能是有利的,因为预定义词典潜在地具有比训练图像数据库更好的行为。 DCMRM模型还利用基于内容的技术和图像搜索技术来定义图像注释中涉及的单词到图像和单词对字的关系。 可以通过使用图像搜索技术对网络数据以及可用的训练数据来估计这两个关系。

    Detecting duplicate images using hash code grouping
    5.
    发明授权
    Detecting duplicate images using hash code grouping 有权
    使用哈希码分组检测重复的图像

    公开(公告)号:US07647331B2

    公开(公告)日:2010-01-12

    申请号:US11277727

    申请日:2006-03-28

    CPC分类号: G06F17/30864

    摘要: A duplicate image detection system generates an image table that maps hash codes of images to their corresponding images. The image table may group images according to their group identifiers generated from the most significant elements of the hash codes based on significance of the elements in representing an image. The image table thus segregates images by their group identifiers. To detect a duplicate image of a target image, the detection system generates a target hash code for the target image. The detection system then identifies the group of the target image based on the group identifier of the target hash code. After identifying the group identifier, the detection system searches the corresponding group table to identify hash codes that have values that are similar to the target hash code. The detection system then selects the images associated with those similar hash codes as being duplicates of the target image.

    摘要翻译: 复制图像检测系统生成将图像的哈希码映射到其对应图像的图像表。 图像表可以根据基于代表图像的元素的重要性从哈希码的最重要元素生成的组标识符来对图像进行分组。 因此,图像表通过其组标识符隔离图像。 为了检测目标图像的重复图像,检测系统生成目标图像的目标散列码。 然后,检测系统基于目标散列码的组标识符来识别目标图像的组。 在识别组标识符之后,检测系统搜索对应的组表以识别具有与目标散列码相似的值的散列码。 然后,检测系统选择与这些类似的哈希码相关联的图像作为目标图像的重复。

    Detecting Duplicate Images Using Hash Code Grouping
    6.
    发明申请
    Detecting Duplicate Images Using Hash Code Grouping 有权
    使用哈希代码分组检测重复的图像

    公开(公告)号:US20070239756A1

    公开(公告)日:2007-10-11

    申请号:US11277727

    申请日:2006-03-28

    IPC分类号: G06F7/00

    CPC分类号: G06F17/30864

    摘要: A duplicate image detection system generates an image table that maps hash codes of images to their corresponding images. The image table may group images according to their group identifiers generated from the most significant elements of the hash codes based on significance of the elements in representing an image. The image table thus segregates images by their group identifiers. To detect a duplicate image of a target image, the detection system generates a target hash code for the target image. The detection system then identifies the group of the target image based on the group identifier of the target hash code. After identifying the group identifier, the detection system searches the corresponding group table to identify hash codes that have values that are similar to the target hash code. The detection system then selects the images associated with those similar hash codes as being duplicates of the target image.

    摘要翻译: 复制图像检测系统生成将图像的哈希码映射到其对应图像的图像表。 图像表可以根据基于代表图像的元素的重要性从哈希码的最重要元素生成的组标识符来对图像进行分组。 因此,图像表通过其组标识符隔离图像。 为了检测目标图像的重复图像,检测系统生成目标图像的目标散列码。 然后,检测系统基于目标散列码的组标识符来识别目标图像的组。 在识别组标识符之后,检测系统搜索对应的组表以识别具有与目标散列码相似的值的散列码。 然后,检测系统选择与这些类似的哈希码相关联的图像作为目标图像的重复。

    OBJECT SIMILARITY SEARCH IN HIGH-DIMENSIONAL VECTOR SPACES
    7.
    发明申请
    OBJECT SIMILARITY SEARCH IN HIGH-DIMENSIONAL VECTOR SPACES 有权
    对象相似性搜索在高维矢量空间

    公开(公告)号:US20080263042A1

    公开(公告)日:2008-10-23

    申请号:US11737075

    申请日:2007-04-18

    IPC分类号: G06F7/08

    摘要: An object search system generates a hierarchical clustering of objects of a collection based on similarity of the objects. The object search system generates a separate hierarchical clustering of objects for multiple features of the objects. To identify objects similar to a target object, the object search system first generates a feature vector for the target object. For each feature of the feature vector, the object search system uses the hierarchical clustering of objects to identify the cluster of objects that is most “feature similar” to that feature of the target object. The object search system indicates the similarity of each candidate object based on the features for which the candidate object is similar.

    摘要翻译: 对象搜索系统基于对象的相似性生成集合的对象的分层聚类。 对象搜索系统为对象的多个特征生成对象的单独层次聚类。 为了识别与目标对象类似的对象,对象搜索系统首先生成目标对象的特征向量。 对于特征向量的每个特征,对象搜索系统使用对象的分层聚类来识别与目标对象的特征最“特征相似”的对象簇。 对象搜索系统基于候选对象相似的特征来指示每个候选对象的相似性。

    OBJECT SIMILARITY SEARCH IN HIGH-DIMENSIONAL VECTOR SPACES
    8.
    发明申请
    OBJECT SIMILARITY SEARCH IN HIGH-DIMENSIONAL VECTOR SPACES 有权
    对象相似性搜索在高维矢量空间

    公开(公告)号:US20110194780A1

    公开(公告)日:2011-08-11

    申请号:US13092083

    申请日:2011-04-21

    IPC分类号: G06K9/68

    摘要: An object search system generates a hierarchical clustering of objects of a collection based on similarity of the objects. The object search system generates a separate hierarchical clustering of objects for multiple features of the objects. To identify objects similar to a target object, the object search system first generates a feature vector for the target object. For each feature of the feature vector, the object search system uses the hierarchical clustering of objects to identify the cluster of objects that is most “feature similar” to that feature of the target object. The object search system indicates the similarity of each candidate object based on the features for which the candidate object is similar.

    摘要翻译: 对象搜索系统基于对象的相似性生成集合的对象的分层聚类。 对象搜索系统为对象的多个特征生成对象的单独分层聚类。 为了识别与目标对象类似的对象,对象搜索系统首先生成目标对象的特征向量。 对于特征向量的每个特征,对象搜索系统使用对象的分层聚类来识别与目标对象的特征最“特征相似”的对象簇。 对象搜索系统基于候选对象相似的特征来指示每个候选对象的相似性。

    Object similarity search in high-dimensional vector spaces
    9.
    发明授权
    Object similarity search in high-dimensional vector spaces 有权
    高维向量空间中的对象相似度搜索

    公开(公告)号:US08224849B2

    公开(公告)日:2012-07-17

    申请号:US13092083

    申请日:2011-04-21

    IPC分类号: G06F7/00 G06F17/30

    摘要: An object search system generates a hierarchical clustering of objects of a collection based on similarity of the objects. The object search system generates a separate hierarchical clustering of objects for multiple features of the objects. To identify objects similar to a target object, the object search system first generates a feature vector for the target object. For each feature of the feature vector, the object search system uses the hierarchical clustering of objects to identify the cluster of objects that is most “feature similar” to that feature of the target object. The object search system indicates the similarity of each candidate object based on the features for which the candidate object is similar.

    摘要翻译: 对象搜索系统基于对象的相似性生成集合的对象的分层聚类。 对象搜索系统为对象的多个特征生成对象的单独分层聚类。 为了识别与目标对象类似的对象,对象搜索系统首先生成目标对象的特征向量。 对于特征向量的每个特征,对象搜索系统使用对象的分层聚类来识别与目标对象的特征最“特征相似”的对象簇。 对象搜索系统基于候选对象相似的特征来指示每个候选对象的相似性。

    Object similarity search in high-dimensional vector spaces
    10.
    发明授权
    Object similarity search in high-dimensional vector spaces 有权
    高维向量空间中的对象相似度搜索

    公开(公告)号:US07941442B2

    公开(公告)日:2011-05-10

    申请号:US11737075

    申请日:2007-04-18

    IPC分类号: G06F7/00 G06F17/30

    摘要: An object search system generates a hierarchical clustering of objects of a collection based on similarity of the objects. The object search system generates a separate hierarchical clustering of objects for multiple features of the objects. To identify objects similar to a target object, the object search system first generates a feature vector for the target object. For each feature of the feature vector, the object search system uses the hierarchical clustering of objects to identify the cluster of objects that is most “feature similar” to that feature of the target object. The object search system indicates the similarity of each candidate object based on the features for which the candidate object is similar.

    摘要翻译: 对象搜索系统基于对象的相似性生成集合的对象的分层聚类。 对象搜索系统为对象的多个特征生成对象的单独分层聚类。 为了识别与目标对象类似的对象,对象搜索系统首先生成目标对象的特征向量。 对于特征向量的每个特征,对象搜索系统使用对象的分层聚类来识别与目标对象的特征最“特征相似”的对象簇。 对象搜索系统基于候选对象相似的特征来指示每个候选对象的相似性。