-
Patent Agency Ranking
公开(公告)号：US20150235097A1
公开(公告)日：2015-08-20
申请号：US14184997
申请日：2014-02-20
Applicant: Google Inc.
Inventor： Li-Lun Wang , Thomas Deselaers , Henry Allan Rowley
CPC classification number: G06K9/00865 , G06K9/00402 , G06K9/222 , G06K9/342 , G06K9/4604 , G06K9/6256 , G06K9/66 , G06N99/005
Abstract: Techniques are provided for segmenting an input by cut point classification and training a cut classifier. A method may include receiving, by a computerized text recognition system, an input in a script. A heuristic may be applied to the input to insert multiple cut points. For each of the cut points, a probability may be generated and the probability may indicate a likelihood that the cut point is correct. Multiple segments of the input may be selected, and the segments may be defined by cut points having a probability over a threshold. Next, the segments of the input may be provided to a character recognizer. Additionally, a method may include training a cut classifier using a machine learning technique, based on multiple text training examples, to determine the correctness of a cut point in an input.
Abstract translation: 提供了通过切点分类对输入进行分割和训练切分分类器的技术。 方法可以包括通过计算机化的文本识别系统接收脚本中的输入。 可以将启发式应用于输入以插入多个切割点。 对于每个切割点，可以产生概率，并且概率可以指示切割点是正确的可能性。 可以选择输入的多个段，并且可以通过具有超过阈值的概率的切点来定义段。 接下来，可以将输入的段提供给字符识别器。 另外，一种方法可以包括基于多个文本训练示例使用机器学习技术来训练切割分类器，以确定输入中的切割点的正确性。
-
公开(公告)号：US09418281B2
公开(公告)日：2016-08-16
申请号：US14142964
申请日：2013-12-30
Applicant: Google Inc.
Inventor： Henry Allan Rowley , Thomas Deselaers , Li-Lun Wang
CPC classification number: G06K9/00402
Abstract: Implementations of the disclosed subject matter provide methods and systems for identifying a candidate character cut for an overwritten character. A method may include providing a handwriting input area. The handwriting input area may be divided into multiple sections and a first portion of the multiple sections may be located in an end point region. A first handwritten input comprising a first stroke that ends in a section located in the end point region may be received. A second handwritten input comprising a second stroke that begins in a section that is not located in the end point region may be received. As a result, a first candidate character cut may be identified between the first stroke and the second stroke.
Abstract translation: 所公开的主题的实现提供了用于识别覆盖字符的候选字符切割的方法和系统。 方法可以包括提供手写输入区域。 手写输入区域可以被分成多个部分，并且多个部分的第一部分可以位于终点区域中。 可以接收包括在位于终点区域中的部分中结束的第一笔划的第一手写输入。 可以接收包括在不位于终点区域的部分中开始的第二笔划的第二手写输入。 结果，可以在第一行程和第二行程之间识别第一候选字符切割。
-
公开(公告)号：US20150186718A1
公开(公告)日：2015-07-02
申请号：US14142964
申请日：2013-12-30
Applicant: Google Inc.
Inventor： Henry Allan Rowley , Thomas Deselaers , Li-Lun Wang
IPC: G06K9/00
CPC classification number: G06K9/00402
Abstract: Implementations of the disclosed subject matter provide methods and systems for identifying a candidate character cut for an overwritten character. A method may include providing a handwriting input area. The handwriting input area may be divided into multiple sections and a first portion of the multiple sections may be located in an end point region. A first handwritten input comprising a first stroke that ends in a section located in the end point region may be received. A second handwritten input comprising a second stroke that begins in a section that is not located in the end point region may be received. As a result, a first candidate character cut may be identified between the first stroke and the second stroke.
Abstract translation: 所公开的主题的实现提供了用于识别覆盖字符的候选字符切割的方法和系统。 方法可以包括提供手写输入区域。 手写输入区域可以被分成多个部分，并且多个部分的第一部分可以位于终点区域中。 可以接收包括在位于终点区域中的部分中结束的第一笔划的第一手写输入。 可以接收包括在不位于终点区域的部分中开始的第二笔划的第二手写输入。 结果，可以在第一行程和第二行程之间识别第一候选字符切割。
-
公开(公告)号：US20170289337A1
公开(公告)日：2017-10-05
申请号：US15090836
申请日：2016-04-05
Applicant: Google Inc.
Inventor： Li-Lun Wang , Victor Carbune , Dhyanesh Narayanan , Henry Rowley , Thomas Deselaers
IPC: H04M1/725 , G06N3/08 , G06F3/0488 , G06F3/0484 , G06F17/24
CPC classification number: H04M1/72552 , G06F3/0484 , G06F3/04883 , G06F17/242 , G06F17/243 , G06N3/08 , H04M2250/70
Abstract: The present disclosure provides systems and methods for text entry through handwritten shorthand stroke patterns. One example computer-implemented method includes receiving, by a mobile computing device, data descriptive of an input stroke pattern entered by a user. The input stroke pattern includes one or more strokes that approximate a non-linguistic symbol. The method includes identifying, by the mobile computing devices, one of a plurality of shorthand stroke patterns as a matched shorthand pattern to which the input stroke pattern corresponds. The plurality of shorthand stroke patterns have been previously defined by the user. A plurality of output text strings are respectively associated with the plurality of shorthand stroke patterns. The method further includes, in response to identifying the matched shorthand pattern, entering, by the mobile computing device, the output text string associated with the matched shorthand pattern into a text entry field.
-
公开(公告)号：US09286527B2
公开(公告)日：2016-03-15
申请号：US14184997
申请日：2014-02-20
Applicant: Google Inc.
Inventor： Li-Lun Wang , Thomas Deselaers , Henry Allan Rowley
CPC classification number: G06K9/00865 , G06K9/00402 , G06K9/222 , G06K9/342 , G06K9/4604 , G06K9/6256 , G06K9/66 , G06N99/005
Abstract: Techniques are provided for segmenting an input by cut point classification and training a cut classifier. A method may include receiving, by a computerized text recognition system, an input in a script. A heuristic may be applied to the input to insert multiple cut points. For each of the cut points, a probability may be generated and the probability may indicate a likelihood that the cut point is correct. Multiple segments of the input may be selected, and the segments may be defined by cut points having a probability over a threshold. Next, the segments of the input may be provided to a character recognizer. Additionally, a method may include training a cut classifier using a machine learning technique, based on multiple text training examples, to determine the correctness of a cut point in an input.
Abstract translation: 提供了通过切点分类对输入进行分割和训练切分分类器的技术。 方法可以包括通过计算机化的文本识别系统接收脚本中的输入。 可以将启发式应用于输入以插入多个切割点。 对于每个切割点，可以产生概率，并且概率可以指示切割点是正确的可能性。 可以选择输入的多个段，并且可以通过具有超过阈值的概率的切点来定义段。 接下来，可以将输入的段提供给字符识别器。 另外，一种方法可以包括基于多个文本训练示例使用机器学习技术来训练切割分类器，以确定输入中的切割点的正确性。
-
-
-
-
Search Results
5
records
(took 0.011 seconds)
