-
1.
公开(公告)号:US08571264B2
公开(公告)日:2013-10-29
申请号:US13209779
申请日:2011-08-15
Applicant: Konstantin Anisimovich , Vadim Tereshchenko , Alexander Shamis
Inventor: Konstantin Anisimovich , Vadim Tereshchenko , Alexander Shamis
CPC classification number: G06K9/6878 , G06K9/468 , G06K2209/01
Abstract: A method and system for recognizing all varieties of objects in an image by using structure models are disclosed. Structural elements are sought when comparing a structural model with an image but only within a framework of one or more generated hypotheses. The method for identifying objects includes preliminarily creating a structural model of objects by specifying a plurality of basic geometric structural elements corresponding to one or more portions of the object, recording a spatial characteristic of each identified basic geometric structural element, and recording a relational characteristic for each specified basic geometric structural element. Objects in the image are isolated and a list of hypotheses for each object is provided. Hypotheses are tested by determining if the corresponding group of basic geometric structural elements corresponds to another supposed object described in a classifier. Results of testing of hypotheses may be saved and the results may be used to identify objects.
Abstract translation: 公开了通过使用结构模型识别图像中的各种物体的方法和系统。 当将结构模型与图像进行比较但仅在一个或多个生成的假设的框架内时,寻求结构元素。 用于识别对象的方法包括通过指定与对象的一个或多个部分相对应的多个基本几何结构元素来初步创建对象的结构模型,记录每个识别的基本几何结构元素的空间特征,并且记录关系特征 每个指定的基本几何结构元素。 图像中的对象被隔离,并提供每个对象的假设列表。 通过确定对应的基本几何结构元素组是否对应于分类器中描述的另一假定对象来测试假设。 可以节省假设检验结果,结果可用于识别物体。
-
公开(公告)号:US07088873B2
公开(公告)日:2006-08-08
申请号:US10386544
申请日:2003-03-13
Applicant: Konstantin Anisimovich , Vadim Tereshchenko , Vladimir Rybkin , Dmitry Vnuchkov
Inventor: Konstantin Anisimovich , Vadim Tereshchenko , Vladimir Rybkin , Dmitry Vnuchkov
IPC: G06K9/03
CPC classification number: G06K9/72 , G06K2209/01
Abstract: A method is described of bit-mapped image analysis comprising division of all analysis means at one's disposal into several groups differing in accuracy and further processing multi-stage analysis.The analysis comprises a primary analysis stage and at least one profound analysis stage, with supplemental data collected at both stages.The primary analysis, includes preliminary recognition of objects with distortion and detection of objects that require more precise analysis means to overcome the distortion. At the primary analysis stage, the analysis means from the group of the most inaccurate group are used.The profound analysis stage includes repeating recognition of objects with a distortion taking into account the supplemental data obtained at the previous stage, detecting objects that require more precise analysis means to overcome the distortion, and collection of newly appeared supplemental data. Each subsequent profound analysis stage uses analysis means from the group of more accurate means.
Abstract translation: 描述了一种位映射图像分析的方法,包括将所有分析装置分配到几组精度不同而进一步处理多级分析。
-
公开(公告)号:US08103103B2
公开(公告)日:2012-01-24
申请号:US10386541
申请日:2003-03-13
Applicant: Konstantin Anisimovich , Vadim Tereshchenko , Vladimir Rybkin , Dmitry Vnuchkov
Inventor: Konstantin Anisimovich , Vadim Tereshchenko , Vladimir Rybkin , Dmitry Vnuchkov
IPC: G06K9/46
CPC classification number: G06K9/00442
Abstract: The present invention discloses a multilevel method of bitmapped image analysis that comprises a whole image data representation via its components—objects of different levels of complexity—hierarchically connected therebetween by spatially-parametrical links. The said method comprises preliminarily generating a classifier of the objects that possibly may be present in the image consisting of one or more levels differing in complexity; parsing the image into objects; attaching each object to one of predetermined levels; establishing hierarchical links between objects of different levels; establishing links between objects within the same level; and performing an object feature analysis. The objects feature analysis comprises at least generating and examining a hypothesis about object features and correcting the object's features of the same and other levels in response to the hypothesis examination results. The step of object features analysis may also comprise execution of a recursive RX-cut within the same level.
Abstract translation: 本发明公开了一种位图图像分析的多级方法,其包括通过其组件的整体图像数据表示 - 通过空间参数链接层级连接在其间的不同复杂级别的对象。 所述方法包括预先生成可能存在于由复杂度不同的一个或多个级别组成的图像中的对象的分类器; 将图像解析成对象; 将每个物体附接到预定水平之一; 建立不同层次对象之间的分层联系; 建立同级别对象之间的链接; 并执行对象特征分析。 对象特征分析至少包括生成和检查关于对象特征的假设,并且响应于假设检查结果来校正相同和其他级别的对象的特征。 对象特征分析的步骤还可以包括在相同水平内执行递归RX切割。
-
公开(公告)号:US20110091111A1
公开(公告)日:2011-04-21
申请号:US10386541
申请日:2003-03-13
Applicant: Konstantin Anisimovich , Vadim Tereshchenko , Vladimir Rybkin , Dmitry Vnuchkov
Inventor: Konstantin Anisimovich , Vadim Tereshchenko , Vladimir Rybkin , Dmitry Vnuchkov
IPC: G06K9/46
CPC classification number: G06K9/00442
Abstract: The present invention discloses a multilevel method of bit-mapped image analysis that comprises a whole image data representation via its components—objects of different levels of complexity—hierarchically connected therebetween by spatially-parametrical links.The said method comprises preliminarily generating a classifier of the objects that possibly may be present in the image consisting of one or more levels differing in complexity; parsing the image into objects; attaching each object to one of predetermined levels; establishing hierarchical links between objects of different levels; establishing links between objects within the same level; performing an objects features analysis.The objects feature analysis comprises at least generating and examining a hypothesis about object features and correcting the concerned objects' features of the same and other levels in response to the hypothesis examination results. The step of objects' features analysis may also comprise execution of a recursive RX-cut within the same level.
Abstract translation: 本发明公开了一种位图映射图像分析的多级方法,其包括经由其组件的整体图像数据表示 - 通过空间参数链路在其间分层连接的不同复杂级别的对象。 所述方法包括预先生成可能存在于由复杂度不同的一个或多个级别组成的图像中的对象的分类器; 将图像解析成对象; 将每个物体附接到预定水平中的一个; 建立不同层次对象之间的分层联系; 建立同级别对象之间的链接; 执行对象特征分析。 对象特征分析至少包括生成和检查关于对象特征的假设,并且响应于假设检查结果来校正相同和其他级别的相关对象的特征。 对象特征分析的步骤还可以包括在相同水平内执行递归RX切割。
-
5.
公开(公告)号:US20110299735A1
公开(公告)日:2011-12-08
申请号:US13209779
申请日:2011-08-15
Applicant: Konstantin Anisimovich , Vadim Tereshchenko , Alexander Shamis
Inventor: Konstantin Anisimovich , Vadim Tereshchenko , Alexander Shamis
CPC classification number: G06K9/6878 , G06K9/468 , G06K2209/01
Abstract: A method and system for recognizing all varieties of objects in an image by using structure models are disclosed. Structural elements are sought when comparing a structural model with an image but only within a framework of one or more generated hypotheses. The method for identifying objects includes preliminarily creating a structural model of objects by specifying a plurality of basic geometric structural elements corresponding to one or more portions of the object, recording a spatial characteristic of each identified basic geometric structural element, and recording a relational characteristic for each specified basic geometric structural element. Objects in the image are isolated and a list of hypotheses for each object is provided. Hypotheses are tested by determining if the corresponding group of basic geometric structural elements corresponds to another supposed object described in a classifier. Results of testing of hypotheses may be saved and the results may be used to identify objects.
Abstract translation: 公开了通过使用结构模型识别图像中的各种物体的方法和系统。 当将结构模型与图像进行比较但仅在一个或多个生成的假设的框架内时,寻求结构元素。 用于识别对象的方法包括通过指定与对象的一个或多个部分相对应的多个基本几何结构元素来初步创建对象的结构模型,记录每个识别的基本几何结构元素的空间特征,并且记录关系特征 每个指定的基本几何结构元素。 图像中的对象被隔离,并提供每个对象的假设列表。 通过确定对应的基本几何结构元素组是否对应于分类器中描述的另一假定对象来测试假设。 可以节省假设检验结果,结果可用于识别物体。
-
公开(公告)号:US07769235B2
公开(公告)日:2010-08-03
申请号:US10241638
申请日:2002-09-12
Applicant: Konstantin Anisimovich , Vadim Tereshchenko , Vladimir Rybkin , Sergey Platonov
Inventor: Konstantin Anisimovich , Vadim Tereshchenko , Vladimir Rybkin , Sergey Platonov
CPC classification number: G06K9/6255 , G06K9/72 , G06K2209/01
Abstract: The present invention discloses a method of character and text recognition of a bit-mapped graphic file received from an optical scanning device. The method comprises a trainable template cache, a preliminarily trained feature analysis means, and a context analysis means. The present invention discloses the way to use said means for achieving the best results in recognition. The method supposes that the template cache along with the context analysis means are used as the main shape characteristic analyzing means. The feature analysis means along with the context analysis means are used as subsidiary shape characteristic analyzing means and as a training means for the template cache. The method comprises applying the main shape characteristic analyzing means and optionally applying the subsidiary shape characteristic analyzing means if no or not enough reliability of recognition is achieved after the template cache analyzing. The obtained results are analyzed and sent to the template cache for template training.
Abstract translation: 本发明公开了一种从光学扫描装置接收的位图图形文件的字符和文本识别方法。 该方法包括可训练的模板高速缓存,预先训练的特征分析装置和上下文分析装置。 本发明公开了使用所述装置获得最佳识别结果的方法。 该方法假设模板高速缓存与上下文分析装置一起被用作主要形状特征分析装置。 将特征分析装置与上下文分析装置一起用作辅助形状特征分析装置以及作为模板高速缓存的训练装置。 该方法包括应用主形状特征分析装置,并且如果在模板高速缓存分析之后没有获得足够的识别可靠性,则可选地应用辅助形状特征分析装置。 获得的结果被分析并发送到模板缓存用于模板训练。