公开(公告)号：US09147105B2

公开(公告)日：2015-09-29

申请号：US13604362

申请日：2012-09-05

申请人： Naotsugu Sagawa ,  Kotaro Yano

发明人： Naotsugu Sagawa ,  Kotaro Yano

IPC分类号： G06K9/00 ,  G06K9/32

CPC分类号： G06K9/00221 ,  G06K9/00362 ,  G06K9/3233

摘要： An image recognizing apparatus is equipped with: a detecting unit configured to detect, from an input image, a candidate area for a target of recognition, based on a likelihood of a partial area in the input image; an extracting unit configured to extract, from a plurality of candidate areas detected by the detecting unit, a set of the candidate areas which are in an overlapping relation; a classifying unit configured to classify an overlapping state of the set of the candidate areas; and a discriminating unit configured to discriminate whether or not the respective candidate areas are the target of recognition, based on the overlapping state of the set of the candidate areas and the respective likelihoods of the candidate areas.

摘要翻译： 图像识别装置具有：检测单元，被配置为基于输入图像中的部分区域的可能性，从输入图像检测用于识别目标的候选区域; 提取单元，被配置为从所述检测单元检测到的多个候选区域提取一组重叠关系的候选区域; 分类单元，被配置为对所述候选区域的集合的重叠状态进行分类; 以及鉴别单元，被配置为基于候选区域的集合的重叠状态和候选区域的各自的可能性来区分各个候选区域是否是识别的目标。

公开(公告)号：US09135524B2

公开(公告)日：2015-09-15

申请号：US13455011

申请日：2012-04-24

申请人： Naotsugu Sagawa ,  Kotaro Yano ,  Satoshi Yashiro

发明人： Naotsugu Sagawa ,  Kotaro Yano ,  Satoshi Yashiro

IPC分类号： G06K9/62

CPC分类号： G06K9/6256 ,  G06K9/6277

摘要： A recognition apparatus includes a calculation unit configured to calculate likelihood of each feature quantity based on the weighted distribution of the feature quantity extracted from a plurality of learning images, a correction unit configured, if a ratio of a learning image to a specific feature quantity is equal to or smaller than a predetermined ratio and a weight for the specific feature quantity is greater than a predetermined value, to correct the value of likelihood of the specific feature quantity to lower the value based on the distribution, a setting unit configured to set the likelihood corrected by the correction unit in association with a feature quantity, and a discrimination unit to extract a feature quantity from an input image and discriminate whether the input image includes a predetermined object based on the likelihood associated with the feature quantity.

摘要翻译： 识别装置包括：计算单元，被配置为基于从多个学习图像提取的特征量的加权分布来计算每个特征量的似然性;校正单元，如果学习图像与特定特征量的比率是 等于或小于预定比例并且特定特征量的权重大于预定值，以校正特定特征量的似然值以便基于分布来降低该值，设置单元，被配置为 与特征量相关联地由校正单元校正的可能性;以及鉴别单元，用于从输入图像中提取特征量，并且基于与特征量相关联的可能性鉴别输入图像是否包括预定对象。

公开(公告)号：US08643739B2

公开(公告)日：2014-02-04

申请号：US12902876

申请日：2010-10-12

申请人： Naotsugu Sagawa

发明人： Naotsugu Sagawa

IPC分类号： H04N5/228 ,  H04N7/18 ,  G06K9/46 ,  G06K9/66 ,  G06K9/62 ,  G06K9/74 ,  G06K9/68

CPC分类号： H04N5/232 ,  G06K9/3233 ,  G06K9/6254 ,  H04N5/23216 ,  H04N5/23219

摘要： An image recognition apparatus includes: a storage unit configured to store a dictionary used to recognize a predetermined pattern; a recognition unit configured to detect in image data using the dictionary, as recognition results, a plurality of partial regions having a likelihood of being the predetermined pattern greater than a predetermined threshold; a display unit configured to display the image data, and also display information indicating the partial regions that were detected by the recognition unit; a determination unit configured to determine, based on an instruction by a user, a negative region from among the plurality of partial regions that were detected by the recognition unit; a generation unit configured to generate a learning image based on the determined negative region; and an update unit configured to update the dictionary based on the learning image that was generated by the generation unit.

摘要翻译： 图像识别装置包括：存储单元，被配置为存储用于识别预定图案的字典; 识别单元，被配置为使用所述字典来检测图像数据，作为识别结果，具有大于预定阈值的预定图案的可能性的多个部分区域; 显示单元，被配置为显示图像数据，并且还显示指示由识别单元检测到的部分区域的信息; 确定单元，被配置为基于用户的指令来确定由所述识别单元检测到的所述多个部分区域中的负区域; 生成单元，被配置为基于所确定的负区域生成学习图像; 以及更新单元，被配置为基于由所述生成单元生成的学习图像来更新所述字典。

公开(公告)号：US20130064425A1

公开(公告)日：2013-03-14

申请号：US13604362

申请日：2012-09-05

申请人： Naotsugu Sagawa ,  Kotaro Yano

发明人： Naotsugu Sagawa ,  Kotaro Yano

IPC分类号： G06K9/62

CPC分类号： G06K9/00221 ,  G06K9/00362 ,  G06K9/3233

摘要： An image recognizing apparatus is equipped with: a detecting unit configured to detect, from an input image, a candidate area for a target of recognition, based on a likelihood of a partial area in the input image; an extracting unit configured to extract, from a plurality of candidate areas detected by the detecting unit, a set of the candidate areas which are in an overlapping relation; a classifying unit configured to classify an overlapping state of the set of the candidate areas; and a discriminating unit configured to discriminate whether or not the respective candidate areas are the target of recognition, based on the overlapping state of the set of the candidate areas and the respective likelihoods of the candidate areas.

摘要翻译： 图像识别装置具有：检测单元，被配置为基于输入图像中的部分区域的可能性，从输入图像检测用于识别目标的候选区域; 提取单元，被配置为从所述检测单元检测到的多个候选区域提取一组重叠关系的候选区域; 分类单元，被配置为对所述候选区域的集合的重叠状态进行分类; 以及鉴别单元，被配置为基于候选区域的集合的重叠状态和候选区域的各自的可能性来区分各个候选区域是否是识别的目标。

公开(公告)号：US20110033117A1

公开(公告)日：2011-02-10

申请号：US12844641

申请日：2010-07-27

申请人： Naotsugu Sagawa

发明人： Naotsugu Sagawa

IPC分类号： G06K9/48

CPC分类号： G06T7/44

摘要： For each pixel of interest in a local region of an input image, an edge intensity in each of a plurality of predetermined directions is calculated. All directions in which the edge intensities are larger than an average value of the edge intensities are selected. For all pixels of interest in the local region, the edge intensities calculated for each of the selected directions are accumulated and output as an edge feature amount.

摘要翻译： 对于输入图像的局部区域中的感兴趣的每个像素，计算多个预定方向中的每一个中的边缘强度。 选择边缘强度大于边缘强度的平均值的所有方向。 对于局部区域中的感兴趣的所有像素，对于每个所选择的方向计算的边缘强度被累积并作为边缘特征量输出。

公开(公告)号：US20090169132A1

公开(公告)日：2009-07-02

申请号：US12277462

申请日：2008-11-25

申请人： Naotsugu Sagawa

发明人： Naotsugu Sagawa

IPC分类号： G06K9/36

CPC分类号： G06T11/60

摘要： A method of controlling an image processing apparatus, the method includes inputting a plurality of images; acquiring additional information added to each of the plurality of images; setting control information used to control a layout of the plurality of images in accordance with the additional information; and generating an output image on which each of the plurality of images is configured to have an image size according to the control information of the respective image.

摘要翻译： 一种控制图像处理装置的方法，所述方法包括：输入多个图像; 获取添加到所述多个图像中的每一个的附加信息; 设置用于根据附加信息控制多个图像的布局的控制信息; 以及生成其中每个所述多个图像被配置为具有根据所述各个图像的控制信息的图像大小的输出图像。

公开(公告)号：US08265429B2

公开(公告)日：2012-09-11

申请号：US12277462

申请日：2008-11-25

申请人： Naotsugu Sagawa

发明人： Naotsugu Sagawa

IPC分类号： G06K9/54 ,  G06F17/00

CPC分类号： G06T11/60

摘要： An image processing apparatus, includes an input unit that inputs a plurality of input images. The image processing apparatus also includes an acquisition unit that acquires photographic information added to each of the plurality of input images. The image processing apparatus further includes a first setting unit that sets control information used to control a layout of each of the plurality of input images in accordance with whether or not the photographic information indicates that the respective input image is photographed with emphasis on an object. The image processing apparatus further includes a generator that generates an output image on which each of the plurality of input images is configured to have an image size according to the control information of the respective input image.

摘要翻译： 一种图像处理装置，包括输入多个输入图像的输入单元。 图像处理装置还包括获取单元，其获取添加到多个输入图像中的每一个的图像信息。 图像处理装置还包括：第一设定单元，根据摄影信息是否指示相应的输入图像被强调对象进行拍摄，设定用于控制多个输入图像中的每一个的布局的控制信息。 图像处理装置还包括发生器，其生成其中多个输入图像中的每一个被配置为具有根据各个输入图像的控制信息的图像尺寸的输出图像。

公开(公告)号：US09001219B2

公开(公告)日：2015-04-07

申请号：US13093741

申请日：2011-04-25

申请人： Naotsugu Sagawa ,  Kazuyo Ikeda ,  Yuji Kaneda

发明人： Naotsugu Sagawa ,  Kazuyo Ikeda ,  Yuji Kaneda

IPC分类号： H04N5/228 ,  H04N5/232 ,  H04N1/00 ,  G06K9/32 ,  G06T7/20

CPC分类号： H04N5/23219 ,  G06K9/3233 ,  G06T7/246 ,  G06T2207/30201 ,  H04N1/00684

摘要： An image processing apparatus acquires a plurality of input images which are serially photographed, detects a plurality of object regions from each input image, and associates object regions in a past input image with object regions in a current input image. If any object region that has not been appropriately associated exists in the object regions detected from the past input image, the apparatus calculates object region movement information for each size of the object region based on the object regions mutually associated between the past input image and the current input image, and estimates a position of the object region of the current input image that has not been associated based on the movement information for each size of the object region and a size of the object region that has not been associated.

摘要翻译： 图像处理装置获取串行拍摄的多个输入图像，从每个输入图像检测多个对象区域，并将过去输入图像中的对象区域与当前输入图像中的对象区域相关联。 如果在从过去输入图像检测到的对象区域中存在没有适当关联的任何对象区域，则该装置基于与过去输入图像和前一个输入图像之间相互关联的对象区域来计算对象区域的每个尺寸的对象区域移动信息 当前输入图像，并且基于针对对象区域的每个大小的移动信息和尚未关联的对象区域的大小来估计未被关联的当前输入图像的对象区域的位置。

公开(公告)号：US08355582B2

公开(公告)日：2013-01-15

申请号：US12844641

申请日：2010-07-27

申请人： Naotsugu Sagawa

发明人： Naotsugu Sagawa

IPC分类号： G06K9/48

CPC分类号： G06T7/44

摘要： For each pixel of interest in a local region of an input image, an edge intensity in each of a plurality of predetermined directions is calculated. All directions in which the edge intensities are larger than an average value of the edge intensities are selected. For all pixels of interest in the local region, the edge intensities calculated for each of the selected directions are accumulated and output as an edge feature amount.

摘要翻译： 对于输入图像的局部区域中的感兴趣的每个像素，计算多个预定方向中的每一个中的边缘强度。 选择边缘强度大于边缘强度的平均值的所有方向。 对于局部区域中的感兴趣的所有像素，对于每个所选择的方向计算的边缘强度被累积并作为边缘特征量输出。

公开(公告)号：US20120275692A1

公开(公告)日：2012-11-01

申请号：US13455011

申请日：2012-04-24

申请人： Naotsugu Sagawa ,  Kotaro Yano ,  Satoshi Yashiro

发明人： Naotsugu Sagawa ,  Kotaro Yano ,  Satoshi Yashiro

IPC分类号： G06K9/46 ,  G06K9/62

CPC分类号： G06K9/6256 ,  G06K9/6277

摘要： A recognition apparatus includes a calculation unit configured to calculate likelihood of each feature quantity based on the weighted distribution of the feature quantity extracted from a plurality of learning images, a correction unit configured, if a ratio of a learning image to a specific feature quantity is equal to or smaller than a predetermined ratio and a weight for the specific feature quantity is greater than a predetermined value, to correct the value of likelihood of the specific feature quantity to lower the value based on the distribution, a setting unit configured to set the likelihood corrected by the correction unit in association with a feature quantity, and a discrimination unit to extract a feature quantity from an input image and discriminate whether the input image includes a predetermined object based on the likelihood associated with the feature quantity.

摘要翻译： 识别装置包括：计算单元，被配置为基于从多个学习图像提取的特征量的加权分布来计算每个特征量的似然性;校正单元，如果学习图像与特定特征量的比率是 等于或小于预定比例并且特定特征量的权重大于预定值，以校正特定特征量的似然值以便基于分布来降低该值，设置单元，被配置为 与特征量相关联地由校正单元校正的可能性;以及鉴别单元，用于从输入图像中提取特征量，并且基于与特征量相关联的可能性鉴别输入图像是否包括预定对象。