专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09767353B2 System and method for transcribing historical records into digitized text 有权
公开(公告)号：US09767353B2
公开(公告)日：2017-09-19
申请号：US14841502
申请日：2015-08-31
申请人： Ancestry.com Operations Inc.
发明人： Jack Reese , Michael Murdock , Shawn Reid , Laryn Brown
IPC分类号： G06K9/00 , G06K9/18 , G06K9/52 , G06K9/62
CPC分类号： G06K9/344 , G06K9/00456 , G06K9/00463 , G06K9/00852 , G06K9/00859 , G06K9/03 , G06K9/18 , G06K9/52 , G06K9/6201 , G06K9/6215 , G06K9/6218 , G06K2209/01 , G06T7/70 , G06T2207/30176
摘要： A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors.

2. 发明授权

US09454545B2 Automated field position linking of indexed data to digital images 有权
标题翻译：索引数据与数字图像的自动字段位置链接
公开(公告)号：US09454545B2
公开(公告)日：2016-09-27
申请号：US14472202
申请日：2014-08-28
申请人： Ancestry.com Operations Inc.
发明人： Jack Reese , Shawn Reid , Laryn Brown , Randy Hansen , Mark Oswald
IPC分类号： G06K9/00 , G06F17/30
CPC分类号： G06F17/30256 , G06F17/30011 , G06K9/00456 , G06K9/00483
摘要： According to one embodiment, a method of linking a document image with indexed data is provided. The method may be performed by providing a document image, which is a digitized document having various information. Indexed data is also provided, which is a record that includes information extracted from the document image or a different document image. The process is further performed by identifying a feature of the indexed data and analyzing the document image to determine whether the feature is present within the information of the digitized document. The feature may be information or a characteristic defined by the information extracted from the document image or the different document image. If the feature is present within the information of the digitized document, a determination is made that the indexed data corresponds with the document image and the indexed data is linked with the document image.
摘要翻译：根据一个实施例，提供了将文档图像与索引数据链接的方法。可以通过提供具有各种信息的数字化文档的文档图像来执行该方法。还提供索引数据，其是包括从文档图像或不同文档图像提取的信息的记录。通过识别索引数据的特征并分析文档图像来进一步执行该过程，以确定特征是否存在于数字化文档的信息内。该特征可以是由从文档图像或不同文档图像中提取的信息定义的信息或特征。如果特征存在于数字化文档的信息内，则确定索引数据对应于文档图像，索引数据与文档图像相关联。

3. 发明申请

US20140369606A1 AUTOMATED FIELD POSITION LINKING OF INDEXED DATA TO DIGITAL IMAGES 有权
公开(公告)号：US20140369606A1
公开(公告)日：2014-12-18
申请号：US14472202
申请日：2014-08-28
申请人： Ancestry.com Operations Inc.
发明人： Jack Reese , Shawn Reid , Laryn Brown , Randy Hansen , Mark Oswald
IPC分类号： G06F17/30 , G06K9/00
CPC分类号： G06F17/30256 , G06F17/30011 , G06K9/00456 , G06K9/00483
摘要： According to one embodiment, a method of linking a document image with indexed data is provided. The method may be performed by providing a document image, which is a digitized document having various information. Indexed data is also provided, which is a record that includes information extracted from the document image or a different document image. The process is further performed by identifying a feature of the indexed data and analyzing the document image to determine whether the feature is present within the information of the digitized document. The feature may be information or a characteristic defined by the information extracted from the document image or the different document image. If the feature is present within the information of the digitized document, a determination is made that the indexed data corresponds with the document image and the indexed data is linked with the document image.

4. 发明授权

US11721091B2 Clustering historical images using a convolutional neural net and labeled data bootstrapping 有权
公开(公告)号：US11721091B2
公开(公告)日：2023-08-08
申请号：US17158801
申请日：2021-01-26
申请人： Ancestry.com Operations Inc.
发明人： Laryn Brown , Michael Murdock , Jack Reese , Shawn Reid
IPC分类号： G06V10/82 , G06F18/40 , G06V10/778
CPC分类号： G06V10/82 , G06F18/41 , G06V10/7788
摘要： Systems and methods for classifying historical images. A feature extractor may create feature vectors corresponding to a plurality of images. A first classification of the plurality of images may be performed based on the plurality of feature vectors, which may include assigning a label to each of the plurality of images and assigning a probability for each of the assigned labels. The assigned probability for each of the assigned labels may be related to a statistical confidence that a particular assigned label is correctly assigned to a particular image. A subset of the plurality of images may be displayed to a display device. An input corresponding to replacement of an incorrect label with a corrected label for a certain image may be received from a user. A second classification of the plurality of images based on the input from the user may be performed.

5. 发明授权

US10318846B2 Clustering historical images using a convolutional neural net and labeled data bootstrapping 有权
公开(公告)号：US10318846B2
公开(公告)日：2019-06-11
申请号：US15393008
申请日：2016-12-28
申请人： Ancestry.com Operations Inc.
发明人： Laryn Brown , Michael Murdock , Jack Reese , Shawn Reid
IPC分类号： G06K9/62
摘要： Systems and methods for classifying historical images. A feature extractor may create feature vectors corresponding to a plurality of images. A first classification of the plurality of images may be performed based on the plurality of feature vectors, which may include assigning a label to each of the plurality of images and assigning a probability for each of the assigned labels. The assigned probability for each of the assigned labels may be related to a statistical confidence that a particular assigned label is correctly assigned to a particular image. A subset of the plurality of images may be displayed to a display device. An input corresponding to replacement of an incorrect label with a corrected label for a certain image may be received from a user. A second classification of the plurality of images based on the input from the user may be performed.

6. 发明授权

US09792520B2 System and method for transcribing handwritten records using word grouping with assigned centroids 有权
公开(公告)号：US09792520B2
公开(公告)日：2017-10-17
申请号：US15451781
申请日：2017-03-07
申请人： Ancestry.com Operations Inc.
发明人： Jack Reese , Michael Murdock , Shawn Reid , Laryn Brown
IPC分类号： G06K9/00 , G06K9/34 , G06K9/03 , G06T7/70 , G06K9/52 , G06K9/62
CPC分类号： G06K9/344 , G06K9/00456 , G06K9/00463 , G06K9/00852 , G06K9/00859 , G06K9/03 , G06K9/18 , G06K9/52 , G06K9/6201 , G06K9/6215 , G06K9/6218 , G06K2209/01 , G06T7/70 , G06T2207/30176
摘要： A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors.

7. 发明申请

US20180181843A1 CLUSTERING HISTORICAL IMAGES USING A CONVOLUTIONAL NEURAL NET AND LABELED DATA BOOTSTRAPPING 审中-公开
公开(公告)号：US20180181843A1
公开(公告)日：2018-06-28
申请号：US15393008
申请日：2016-12-28
申请人： Ancestry.com Operations Inc.
发明人： Laryn Brown , Michael Murdock , Jack Reese , Shawn Reid
IPC分类号： G06K9/62 , G06K9/46
CPC分类号： G06K9/6254
摘要： Systems and methods for classifying historical images. A feature extractor may create feature vectors corresponding to a plurality of images. A first classification of the plurality of images may be performed based on the plurality of feature vectors, which may include assigning a label to each of the plurality of images and assigning a probability for each of the assigned labels. The assigned probability for each of the assigned labels may be related to a statistical confidence that a particular assigned label is correctly assigned to a particular image. A subset of the plurality of images may be displayed to a display device. An input corresponding to replacement of an incorrect label with a corrected label for a certain image may be received from a user. A second classification of the plurality of images based on the input from the user may be performed.

8. 发明申请

US20170193323A1 SYSTEM AND METHOD FOR TRANSCRIBING HANDWRITTEN RECORDS USING WORD GROUPING WITH ASSIGNED CENTROIDS 有权
公开(公告)号：US20170193323A1
公开(公告)日：2017-07-06
申请号：US15451781
申请日：2017-03-07
申请人： Ancestry.com Operations Inc.
发明人： Jack Reese , Michael Murdock , Shawn Reid , Laryn Brown
IPC分类号： G06K9/34 , G06K9/62 , G06K9/00 , G06K9/52 , G06K9/03 , G06T7/70
CPC分类号： G06K9/344 , G06K9/00456 , G06K9/00463 , G06K9/00852 , G06K9/00859 , G06K9/03 , G06K9/18 , G06K9/52 , G06K9/6201 , G06K9/6215 , G06K9/6218 , G06K2209/01 , G06T7/70 , G06T2207/30176
摘要： A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors.

9. 发明申请

US20160063355A1 SYSTEM AND METHOD FOR TRANSCRIBING HANDWRITTEN RECORDS USING WORD GROUPING WITH ASSIGNED CENTROIDS 有权
标题翻译：使用分配中心的WORD分组来转换手写记录的系统和方法
公开(公告)号：US20160063355A1
公开(公告)日：2016-03-03
申请号：US14841542
申请日：2015-08-31
申请人： Ancestry.com Operations Inc.
发明人： Jack Reese , Michael Murdock , Shawn Reid , Laryn Brown
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/344 , G06K9/00456 , G06K9/00463 , G06K9/00852 , G06K9/00859 , G06K9/03 , G06K9/18 , G06K9/52 , G06K9/6201 , G06K9/6215 , G06K9/6218 , G06K2209/01 , G06T7/70 , G06T2207/30176
摘要： A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors.
摘要翻译：手写识别系统将诸如历史记录的文档图像的文档上的文字图像转换为计算机可搜索的文本。位于文档上的Word图像（片段），并标识了多个单词特征。对于每个单词图像，创建一个表示多个单词特征的单词特征向量。基于词特征的相似性（例如，特征向量之间的距离），类似的词被分组在一起成簇，并且选择具有群体中最具代表性的特征的质心。基于对集群中的质心的检查，为每个集群选择数字化文本字，并将其分配给该集群中的所有单词，并将其用作在文档中显示的单词图像的计算机可搜索文本。分析人员可以查看群集以允许改进用于在群集中分组单词的参数，包括用于确定特征向量之间的距离的权重和其他因子的调整。

10. 发明申请

US20160063354A1 SYSTEM AND METHOD FOR TRANSCRIBING HANDWRITTEN RECORDS USING WORD GROUPINGS BASED ON FEATURE VECTORS 有权
标题翻译：使用基于特征向量的字组分集手写记录的系统和方法
公开(公告)号：US20160063354A1
公开(公告)日：2016-03-03
申请号：US14841519
申请日：2015-08-31
申请人： Ancestry.com Operations Inc.
发明人： Jack Reese , Michael Murdock , Shawn Reid , Laryn Brown
IPC分类号： G06K9/62 , G06K9/00 , G06K9/52 , G06K9/18
CPC分类号： G06K9/344 , G06K9/00456 , G06K9/00463 , G06K9/00852 , G06K9/00859 , G06K9/03 , G06K9/18 , G06K9/52 , G06K9/6201 , G06K9/6215 , G06K9/6218 , G06K2209/01 , G06T7/70 , G06T2207/30176
摘要： A handwriting recognition system converts word images on documents, such as document images of historical records, into computer searchable text. Word images (snippets) on the document are located, and have multiple word features identified. For each word image, a word feature vector is created representing multiple word features. Based on the similarity of word features (e.g., the distance between feature vectors), similar words are grouped together in clusters, and a centroid that has features most representative of words in the cluster is selected. A digitized text word is selected for each cluster based on review of a centroid in the cluster, and is assigned to all words in that cluster and is used as computer searchable text for those word images where they appear in documents. An analyst may review clusters to permit refinement of the parameters used for grouping words in clusters, including the adjustment of weights and other factors used for determining the distance between feature vectors.
摘要翻译：手写识别系统将诸如历史记录的文档图像的文档上的文字图像转换为计算机可搜索的文本。位于文档上的Word图像（片段），并标识了多个单词特征。对于每个单词图像，创建一个表示多个单词特征的单词特征向量。基于词特征的相似性（例如，特征向量之间的距离），类似的词被分组在一起成簇，并且选择具有群体中最具代表性的特征的质心。基于对集群中的质心的检查，为每个集群选择数字化文本字，并将其分配给该集群中的所有单词，并将其用作在文档中显示的单词图像的计算机可搜索文本。分析人员可以查看群集以允许改进用于在群集中分组单词的参数，包括用于确定特征向量之间的距离的权重和其他因子的调整。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式