公开(公告)号：US08861803B2

公开(公告)日：2014-10-14

申请号：US13436585

申请日：2012-03-30

申请人： Kotaro Yano ,  Hiroshi Sato ,  Shunsuke Nakano

发明人： Kotaro Yano ,  Hiroshi Sato ,  Shunsuke Nakano

IPC分类号： G06K9/46 ,  G06K9/00

CPC分类号： G06K9/00281

摘要： An image recognition apparatus includes an extraction unit configured to extract a feature quantity for each local area from an input image, a conversion unit configured to convert the feature quantity extracted by the extraction unit into a feature quantity indicating a degree with respect to an attribute for each local area, a verification unit configured to verify the feature quantity converted by the conversion unit against a feature quantity of a registered image, and an identification unit configured to identify whether the input image is identical to the registered image by integrating the verification result for each local area acquired by the verification unit.

摘要翻译： 图像识别装置包括：提取单元，被配置为从输入图像中提取每个局部区域的特征量;转换单元，被配置为将由提取单元提取的特征量转换为指示相对于属性的属性的度数的特征量 每个局部区域，验证单元，被配置为验证由转换单元转换的特征量相对于注册图像的特征量;以及识别单元，被配置为通过将输入图像与登记图像相一致来识别， 验证单位获取的每个局部区域。

公开(公告)号：US20120257799A1

公开(公告)日：2012-10-11

申请号：US13436585

申请日：2012-03-30

申请人： Kotaro Yano ,  Hiroshi Sato ,  Shunsuke Nakano

发明人： Kotaro Yano ,  Hiroshi Sato ,  Shunsuke Nakano

IPC分类号： G06K9/46 ,  G06K9/00

CPC分类号： G06K9/00281

摘要： An image recognition apparatus includes an extraction unit configured to extract a feature quantity for each local area from an input image, a conversion unit configured to convert the feature quantity extracted by the extraction unit into a feature quantity indicating a degree with respect to an attribute for each local area, a verification unit configured to verify the feature quantity converted by the conversion unit against a feature quantity of a registered image, and an identification unit configured to identify whether the input image is identical to the registered image by integrating the verification result for each local area acquired by the verification unit.

摘要翻译： 图像识别装置包括：提取单元，被配置为从输入图像中提取每个局部区域的特征量;转换单元，被配置为将由提取单元提取的特征量转换为指示相对于属性的属性的度数的特征量 每个局部区域，验证单元，被配置为验证由转换单元转换的特征量相对于注册图像的特征量;以及识别单元，被配置为通过将输入图像与登记图像相一致来识别， 验证单位获取的每个局部区域。

公开(公告)号：US08842880B2

公开(公告)日：2014-09-23

申请号：US13444738

申请日：2012-04-11

申请人： Shunsuke Nakano ,  Hiroshi Sato ,  Yuji Kaneda ,  Takashi Suzuki

发明人： Shunsuke Nakano ,  Hiroshi Sato ,  Yuji Kaneda ,  Takashi Suzuki

IPC分类号： G06K9/00 ,  G06F3/00

CPC分类号： G06K9/00288

摘要： An information processing apparatus comprising: an obtaining unit configured to obtain image data; a detection unit configured to detect an object from the image data; an attribute determination unit configured to determine an attribute indicating a characteristic of the object detected by the detection unit; a registration unit configured to register the image data in at least one of a plurality of dictionaries based on the attribute determined by the attribute determination unit; and an adding unit configured to add, when the image data is registered in not less than two dictionaries, link information concerning the image data registered in the other dictionary to the image data registered in one dictionary.

摘要翻译： 一种信息处理设备，包括：获取单元，被配置为获得图像数据; 检测单元，被配置为从所述图像数据检测对象; 属性确定单元，被配置为确定指示由所述检测单元检测到的所述对象的特征的属性; 注册单元，被配置为基于由属性确定单元确定的属性将多个字典中的至少一个注册图像数据; 以及添加单元，被配置为当图像数据在不少于两个字典中登记时，将登记在其他字典中的图像数据的链接信息添加到登记在一个字典中的图像数据。

公开(公告)号：US20110103694A1

公开(公告)日：2011-05-05

申请号：US12908480

申请日：2010-10-20

申请人： Shunsuke Nakano ,  Hiroshi Sato

发明人： Shunsuke Nakano ,  Hiroshi Sato

IPC分类号： G06K9/46

CPC分类号： G06K9/00288 ,  G06K9/00281

摘要： An object identification apparatus which identifies an object included in an input image includes a unit which calculates correlation values of feature amounts in standard partial feature regions respectively extracted from the input images and processing targets, and correlation values of feature amounts in adaptive partial feature regions respectively extracted from the input image and processing targets, a unit which calculates similarities based on the calculated correlation values, and a unit which integrates the plurality of calculated similarities, and outputs them as an integrated similarity between the input image and registered image as the processing targets. According to the object identification apparatus, an identification performance between two specific categories, which are similarity to each other, is improved while maintain an overall identification performance.

摘要翻译： 识别输入图像中包含的对象的对象识别装置包括：分别计算从输入图像和处理对象中分别提取出的标准部分特征区域中的特征量的相关值的单位，以及自适应部分特征区域中的特征量的相关值 从输入图像和处理对象中提取的单元，基于计算出的相关值计算相似度的单元，以及将多个计算出的相似度进行积分的单位，并将其输出为输入图像和登记图像之间的综合相似度作为处理对象 。 根据对象识别装置，改善了彼此相似的两个特定类别之间的识别性能，同时保持了整体识别性能。

公开(公告)号：US20110158536A1

公开(公告)日：2011-06-30

申请号：US12973172

申请日：2010-12-20

申请人： Shunsuke Nakano ,  Hiroshi Sato ,  Katsuhiko Mori

发明人： Shunsuke Nakano ,  Hiroshi Sato ,  Katsuhiko Mori

IPC分类号： G06K9/46

CPC分类号： G06K9/00281 ,  G06K9/00926

摘要： An object identification apparatus, which identifies a class of a plurality of registered classes to which an object included in an input image belongs, registers a plurality of registered images used in identification of an input image, and holds designation data required to designate partial areas used in identification. The apparatus extracts feature amounts of the partial areas designated by the designation data from the input image and each of the plurality of registered images, and identifies a class to which the input image belongs based on the extracted feature amounts. The apparatus determines based on the plurality of registered images whether or not is required to update processing contents of an identification unit. When it is determined that the processing contents are required to be updated, the apparatus updates the designation data based on registered images.

摘要翻译： 一种对象识别装置，其识别包含在输入图像中的对象所属的多个注册类别的类别，登记在输入图像的识别中使用的多个登记图像，并保存指定使用的部分区域所需的指定数据 在识别。 该装置从输入图像和多个登记图像中的每一个提取由指定数据指定的部分区域的特征量，并且基于提取的特征量来识别输入图像所属的类别。 该装置基于多个登记图像确定是否需要更新识别单元的处理内容。 当确定需要更新处理内容时，装置基于登记图像来更新指定数据。

公开(公告)号：US08781235B2

公开(公告)日：2014-07-15

申请号：US13208072

申请日：2011-08-11

申请人： Takashi Suzuki ,  Shunsuke Nakano ,  Hiroshi Sato

发明人： Takashi Suzuki ,  Shunsuke Nakano ,  Hiroshi Sato

IPC分类号： G06K9/68 ,  G06K9/62

CPC分类号： G06K9/00295 ,  G06K9/00926 ,  G06K9/6807

摘要： An apparatus extracts a first dictionary information associated with a first category from among multiple categories included in a dictionary and second dictionary information associated with a second category from among multiple categories included in the dictionary or another dictionary, calculates a first feature amount and a second feature amount from the first dictionary information and the second dictionary information, respectively, receives an instruction as to whether or not to integrate a name of the first category and a name of the second category in the case where it is determined that a similarity between the calculated first feature amount and second feature amount is greater than a predetermined threshold and that the name of the first category and the name of the second category do not match, and integrates the name of the first category and the name of the second category with the received post-integration name.

摘要翻译： 一种装置从包括在字典中的多个类别中提取与第一类别相关联的第一字典信息，以及从包括在字典或另一字典中的多个类别中的与第二类别相关联的第二字典信息，计算第一特征量和第二特征 在第一字典信息和第二字典信息中的数量分别接收关于是否将第一类别的名称和第二类别的名称整合的指令，在确定所计算的 第一特征量和第二特征量大于预定阈值，并且第一类别的名称和第二类别的名称不匹配，并且将第一类别的名称和第二类别的名称与所接收的 后整合名称。

公开(公告)号：US08705806B2

公开(公告)日：2014-04-22

申请号：US12973172

申请日：2010-12-20

申请人： Shunsuke Nakano ,  Hiroshi Sato ,  Katsuhiko Mori

发明人： Shunsuke Nakano ,  Hiroshi Sato ,  Katsuhiko Mori

IPC分类号： G06K9/00 ,  G06K9/62 ,  G06K9/66

CPC分类号： G06K9/00281 ,  G06K9/00926

摘要： An object identification apparatus, which identifies a class of a plurality of registered classes to which an object included in an input image belongs, registers a plurality of registered images used in identification of an input image, and holds designation data required to designate partial areas used in identification. The apparatus extracts feature amounts of the partial areas designated by the designation data from the input image and each of the plurality of registered images, and identifies a class to which the input image belongs based on the extracted feature amounts. The apparatus determines based on the plurality of registered images whether or not is required to update processing contents of an identification unit. When it is determined that the processing contents are required to be updated, the apparatus updates the designation data based on registered images.

摘要翻译： 一种对象识别装置，其识别包含在输入图像中的对象所属的多个注册类别的类别，登记在输入图像的识别中使用的多个登记图像，并保存指定使用的部分区域所需的指定数据 在识别。 该装置从输入图像和多个登记图像中的每一个提取由指定数据指定的部分区域的特征量，并且基于提取的特征量来识别输入图像所属的类别。 该装置基于多个登记图像确定是否需要更新识别单元的处理内容。 当确定需要更新处理内容时，装置基于登记图像来更新指定数据。

公开(公告)号：US20120269389A1

公开(公告)日：2012-10-25

申请号：US13444738

申请日：2012-04-11

申请人： Shunsuke Nakano ,  Hiroshi Sato ,  Yuji Kaneda ,  Takashi Suzuki

发明人： Shunsuke Nakano ,  Hiroshi Sato ,  Yuji Kaneda ,  Takashi Suzuki

IPC分类号： G06K9/62

CPC分类号： G06K9/00288

摘要： An information processing apparatus comprising: an obtaining unit configured to obtain image data; a detection unit configured to detect an object from the image data; an attribute determination unit configured to determine an attribute indicating a characteristic of the object detected by the detection unit; a registration unit configured to register the image data in at least one of a plurality of dictionaries based on the attribute determined by the attribute determination unit; and an adding unit configured to add, when the image data is registered in not less than two dictionaries, link information concerning the image data registered in the other dictionary to the image data registered in one dictionary.

摘要翻译： 一种信息处理设备，包括：获取单元，被配置为获得图像数据; 检测单元，被配置为从所述图像数据检测对象; 属性确定单元，被配置为确定指示由所述检测单元检测到的所述对象的特征的属性; 注册单元，被配置为基于由属性确定单元确定的属性将多个字典中的至少一个注册图像数据; 以及添加单元，被配置为当图像数据在不少于两个字典中登记时，将登记在其他字典中的图像数据的链接信息添加到登记在一个字典中的图像数据。

公开(公告)号：US20120051646A1

公开(公告)日：2012-03-01

申请号：US13208072

申请日：2011-08-11

申请人： Takashi Suzuki ,  Shunsuke Nakano ,  Hiroshi Sato

发明人： Takashi Suzuki ,  Shunsuke Nakano ,  Hiroshi Sato

IPC分类号： G06K9/46

CPC分类号： G06K9/00295 ,  G06K9/00926 ,  G06K9/6807

摘要： An apparatus extracts a first dictionary information associated with a first category from among multiple categories included in a dictionary and second dictionary information associated with a second category from among multiple categories included in the dictionary or another dictionary, calculates a first feature amount and a second feature amount from the first dictionary information and the second dictionary information, respectively, receives an instruction as to whether or not to integrate a name of the first category and a name of the second category in the case where it is determined that a similarity between the calculated first feature amount and second feature amount is greater than a predetermined threshold and that the name of the first category and the name of the second category do not match, and integrates the name of the first category and the name of the second category with the received post-integration name.

摘要翻译： 一种装置从包括在字典中的多个类别中提取与第一类别相关联的第一字典信息，以及从包括在字典或另一字典中的多个类别中的与第二类别相关联的第二字典信息，计算第一特征量和第二特征 在第一字典信息和第二字典信息中的数量分别接收关于是否将第一类别的名称和第二类别的名称整合的指令，在确定所计算的 第一特征量和第二特征量大于预定阈值，并且第一类别的名称和第二类别的名称不匹配，并且将第一类别的名称和第二类别的名称与接收的 后整合名称。

公开(公告)号：US08542887B2

公开(公告)日：2013-09-24

申请号：US12908480

申请日：2010-10-20

申请人： Shunsuke Nakano ,  Hiroshi Sato

发明人： Shunsuke Nakano ,  Hiroshi Sato

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/62

CPC分类号： G06K9/00288 ,  G06K9/00281

摘要： An object identification apparatus which identifies an object included in an input image includes a unit which calculates correlation values of feature amounts in standard partial feature regions respectively extracted from the input images and processing targets, and correlation values of feature amounts in adaptive partial feature regions respectively extracted from the input image and processing targets, a unit which calculates similarities based on the calculated correlation values, and a unit which integrates the plurality of calculated similarities, and outputs them as an integrated similarity between the input image and registered image as the processing targets. According to the object identification apparatus, an identification performance between two specific categories, which are similarity to each other, is improved while maintain an overall identification performance.

摘要翻译： 识别输入图像中包含的对象的对象识别装置包括：分别计算从输入图像和处理对象中分别提取出的标准部分特征区域中的特征量的相关值的单位，以及自适应部分特征区域中的特征量的相关值 从输入图像和处理对象中提取的单元，基于计算出的相关值计算相似度的单元，以及将多个计算出的相似度进行积分的单位，并将其输出为输入图像和登记图像之间的综合相似度作为处理对象 。 根据对象识别装置，改善了彼此相似的两个特定类别之间的识别性能，同时保持了整体识别性能。