-
1.发明申请公开(公告)号：US20190050641A1
公开(公告)日：2019-02-14
申请号：US16160975
申请日：2018-10-15
申请人： Tantrum Street LLC
摘要： A system, methods, and apparatus for generating pattern recognition classifiers are disclosed. An example method includes identifying graphical objects within an image of a card object, for each identified graphical object: i) creating a bounding region encompassing the graphical object such that a border of the bounding region is located at a predetermined distance from segments of the graphical object, ii) determining pixels within the bounding region that correspond to the graphical object, iii) determining an origin of the graphical object based on an origin rule, iv) determining a text coordinate relative to the origin for each determined pixel, and v) determining a statistical probability that features are present within the graphical object, each of the features including at least one pixel having text coordinates and for each graphical object type, combining the statistical probabilities for each of the features of the identified graphical objects into a classifier data structure.
-
公开(公告)号：US10133921B2
公开(公告)日：2018-11-20
申请号：US14875397
申请日：2015-10-05
申请人： Tantrum Street LLC
摘要： A system, methods, and apparatus for generating pattern recognition classifiers are disclosed. An example method includes identifying graphical objects within an image of a card object, for each identified graphical object: i) creating a bounding region encompassing the graphical object such that a border of the bounding region is located at a predetermined distance from segments of the graphical object, ii) determining pixels within the bounding region that correspond to the graphical object, iii) determining an origin of the graphical object based on an origin rule, iv) determining a text coordinate relative to the origin for each determined pixel, and v) determining a statistical probability that features are present within the graphical object, each of the features including at least one pixel having text coordinates and for each graphical object type, combining the statistical probabilities for each of the features of the identified graphical objects into a classifier data structure.
-
3.发明授权Methods and apparatus for capturing, processing, training, and detecting patterns using pattern recognition classifiers 有权使用模式识别分类器捕获，处理，训练和检测模式的方法和装置公开(公告)号：US09152860B2
公开(公告)日：2015-10-06
申请号：US13910637
申请日：2013-06-05
申请人： Tantrum Street LLC
CPC分类号： G06K9/00483 , G06K9/00463 , G06K9/00469 , G06K9/46 , G06K9/64 , G06K9/66
摘要： A system, methods, and apparatus for generating pattern recognition classifiers are disclosed. An example method includes identifying graphical objects within an image of a card object, for each identified graphical object: i) creating a bounding region encompassing the graphical object such that a border of the bounding region is located at a predetermined distance from segments of the graphical object, ii) determining pixels within the bounding region that correspond to the graphical object, iii) determining an origin of the graphical object based on an origin rule, iv) determining a text coordinate relative to the origin for each determined pixel, and v) determining a statistical probability that features are present within the graphical object, each of the features including at least one pixel having text coordinates and for each graphical object type, combining the statistical probabilities for each of the features of the identified graphical objects into a classifier data structure.
摘要翻译： 公开了一种用于生成模式识别分类器的系统，方法和装置。 示例性方法包括识别针对每个识别的图形对象的卡对象的图像内的图形对象：i）创建包围图形对象的边界区域，使得边界区域的边界位于与图形的段相距预定距离处 对象，ii）确定所述边界区域内对应于所述图形对象的像素，iii）基于原始规则确定所述图形对象的原点; iv）确定相对于所确定的像素的所述原点的文本坐标，以及v） 确定特征存在于图形对象内的统计概率，每个特征包括至少一个具有文本坐标的像素和每个图形对象类型，将所识别的图形对象的每个特征的统计概率组合成分类器数据 结构体。
-
4.发明申请METHODS AND APPARATUS FOR CAPTURING, PROCESSING, TRAINING, AND DETECTING PATTERNS USING PATTERN RECOGNITION CLASSIFIERS 审中-公开使用图案识别分类器捕获，处理，培训和检测图案的方法和装置公开(公告)号：US20160026861A1
公开(公告)日：2016-01-28
申请号：US14875397
申请日：2015-10-05
申请人： Tantrum Street LLC
CPC分类号： G06K9/00483 , G06K9/00463 , G06K9/00469 , G06K9/46 , G06K9/64 , G06K9/66
摘要： A system, methods, and apparatus for generating pattern recognition classifiers are disclosed. An example method includes identifying graphical objects within an image of a card object, for each identified graphical object: i) creating a bounding region encompassing the graphical object such that a border of the bounding region is located at a predetermined distance from segments of the graphical object, ii) determining pixels within the bounding region that correspond to the graphical object, iii) determining an origin of the graphical object based on an origin rule, iv) determining a text coordinate relative to the origin for each determined pixel, and v) determining a statistical probability that features arc present within the graphical object, each of the features including at least one pixel having text coordinates and for each graphical object type, combining the statistical probabilities for each of the features of the identified graphical objects into a classifier data structure.
摘要翻译： 公开了一种用于生成模式识别分类器的系统，方法和装置。 示例性方法包括识别针对每个识别的图形对象的卡对象的图像内的图形对象：i）创建包围图形对象的边界区域，使得边界区域的边界位于与图形的段相距预定距离处 对象，ii）确定所述边界区域内对应于所述图形对象的像素，iii）基于原始规则确定所述图形对象的原点; iv）确定相对于所确定的像素的所述原点的文本坐标，以及v） 确定特征弧存在于图形对象内的统计概率，每个特征包括至少一个具有文本坐标的像素和每个图形对象类型，将所识别的图形对象的每个特征的统计概率组合成分类器数据 结构体。
-
5.发明申请METHODS AND APPARATUS FOR CAPTURING, PROCESSING, TRAINING, AND DETECTING PATTERNS USING PATTERN RECOGNITION CLASSIFIERS 有权使用图案识别分类器捕获，处理，培训和检测图案的方法和装置公开(公告)号：US20140334721A1
公开(公告)日：2014-11-13
申请号：US13910637
申请日：2013-06-05
申请人： Tantrum Street LLC
CPC分类号： G06K9/00483 , G06K9/00463 , G06K9/00469 , G06K9/46 , G06K9/64 , G06K9/66
摘要： A system, methods, and apparatus for generating pattern recognition classifiers are disclosed. An example method includes identifying graphical objects within an image of a card object, for each identified graphical object: i) creating a bounding region encompassing the graphical object such that a border of the bounding region is located at a predetermined distance from segments of the graphical object, ii) determining pixels within the bounding region that correspond to the graphical object, iii) determining an origin of the graphical object based on an origin rule, iv) determining a text coordinate relative to the origin for each determined pixel, and v) determining a statistical probability that features are present within the graphical object, each of the features including at least one pixel having text coordinates and for each graphical object type, combining the statistical probabilities for each of the features of the identified graphical objects into a classifier data structure.
摘要翻译： 公开了一种用于生成模式识别分类器的系统，方法和装置。 示例性方法包括识别针对每个识别的图形对象的卡对象的图像内的图形对象：i）创建包围图形对象的边界区域，使得边界区域的边界位于与图形的段相距预定距离处 对象，ii）确定所述边界区域内对应于所述图形对象的像素，iii）基于原始规则确定所述图形对象的原点; iv）确定相对于所确定的像素的所述原点的文本坐标，以及v） 确定特征存在于图形对象内的统计概率，每个特征包括至少一个具有文本坐标的像素和每个图形对象类型，将所识别的图形对象的每个特征的统计概率组合成分类器数据 结构体。
-
-
-
-
搜索结果
5 条记录 (耗时 0.013 秒)
