公开(公告)号：US07529425B2

公开(公告)日：2009-05-05

申请号：US11606091

申请日：2006-11-30

申请人： Yoshiro Kitamura ,  Wataru Ito

发明人： Yoshiro Kitamura ,  Wataru Ito

IPC分类号： G06K9/40

CPC分类号： G06K9/40 ,  G06T5/002 ,  G06T5/005 ,  G06T5/20 ,  G06T2207/20012 ,  G06T2207/20192 ,  G06T2207/20224 ,  G06T2207/30196

摘要： A blurred image generating section generates a plurality of blurred images Sm (where m=1 to n and n≧2) different in frequency response characteristic from one another, based on an original image S0. A band-limited image generating section generates a plurality of band-limited images Tm by performing a subtraction between images of adjacent frequency bands, employing the original image S0 and each of the blurred images Sm. A noise component extraction section extracts converted images, obtained by performing nonlinear conversion on each of the band-limited images Tm, as noise components Qm contained in the different frequency bands. A noise-component elimination section subtracts from the original image S0 a value obtained by multiplying a subtraction coefficient β (which is determined according to the pixel value Y0 of the original image S0) and the sum of the noise components Qm together.

摘要翻译： 模糊图像生成部基于原始图像S0生成彼此不同频率响应特性的多个模糊图像Sm（其中m = 1到n和n> = 2）。 频带限制图像生成部分通过使用原始图像S0和模糊图像Sm中的每一个执行相邻频带的图像之间的相减来生成多个带限图像Tm。 噪声分量提取部分提取通过对每个频带限制图像Tm执行非线性转换而获得的转换图像作为包含在不同频带中的噪声分量Qm。 噪声分量消除部分从原始图像S0中减去通过将减法系数β（根据原始图像S0的像素值Y0确定）与噪声分量Qm之和相乘得到的值。

公开(公告)号：US20070122010A1

公开(公告)日：2007-05-31

申请号：US11589888

申请日：2006-10-31

申请人： Yoshiro Kitamura ,  Wataru Ito

发明人： Yoshiro Kitamura ,  Wataru Ito

IPC分类号： G06K9/00

CPC分类号： G06K9/00248

摘要： When detecting a face included in an input image by use of at least two inclinations of the face to be detected, a first detection process is performed if the inclination of the face to be detected corresponds to a first inclination where a relatively high face detection probability is expected, and a second detection process having a relatively low face detection probability and a relatively short processing time compared with the first detection process is performed if the inclination of the face to be detected is other than the first inclination. When an input image is scanned to enable the change in face detection processes according to the position of the face to be detected, a different detection process is used according to the face detection probability of the position of the face to be detected.

摘要翻译： 当通过使用要检测的脸部的至少两个倾斜度来检测包含在输入图像中的脸部时，如果要检测的脸部的倾斜度对应于第一倾斜度，则执行第一检测处理，其中相对较高的面部检测概率 如果要检测的脸部的倾斜度不是第一倾斜度，则执行与第一检测处理相比具有相对低的面部检测概率和相对短的处理时间的第二检测处理。 当输入图像被扫描以根据要检测的面部的位置来进行面部检测处理的改变时，根据要检测的面部的位置的面部检测概率来使用不同的检测处理。

公开(公告)号：US07809173B2

公开(公告)日：2010-10-05

申请号：US11589888

申请日：2006-10-31

申请人： Yoshiro Kitamura ,  Wataru Ito

发明人： Yoshiro Kitamura ,  Wataru Ito

IPC分类号： G06K9/00 ,  G06K9/36

CPC分类号： G06K9/00248

摘要： When detecting a face included in an input image by use of at least two inclinations of the face to be detected, a first detection process is performed if the inclination of the face to be detected corresponds to a first inclination where a relatively high face detection probability is expected, and a second detection process having a relatively low face detection probability and a relatively short processing time compared with the first detection process is performed if the inclination of the face to be detected is other than the first inclination. When an input image is scanned to enable the change in face detection processes according to the position of the face to be detected, a different detection process is used according to the face detection probability of the position of the face to be detected.

摘要翻译： 当通过使用要检测的脸部的至少两个倾斜度来检测包含在输入图像中的脸部时，如果要检测的脸部的倾斜度对应于第一倾斜度，则执行第一检测处理，其中相对较高的面部检测概率 如果要检测的脸部的倾斜度不是第一倾斜度，则执行与第一检测处理相比具有相对低的面部检测概率和相对短的处理时间的第二检测处理。 当输入图像被扫描以根据要检测的面部的位置来进行面部检测处理的改变时，根据要检测的面部的位置的面部检测概率来使用不同的检测处理。

公开(公告)号：US20070189609A1

公开(公告)日：2007-08-16

申请号：US11393680

申请日：2006-03-31

申请人： Wataru Ito ,  Sadato Akahori ,  Kensuke Terakawa ,  Yoshiro Kitamura

发明人： Wataru Ito ,  Sadato Akahori ,  Kensuke Terakawa ,  Yoshiro Kitamura

IPC分类号： G06K9/62 ,  G06K9/46

CPC分类号： G06K9/00281 ,  G06K9/38 ,  G06K9/6292

摘要： A face discriminating process judges whether a discrimination target image is an image of a face, based on characteristic amounts of the discrimination target image. Gradation conversion of pixel values is administered as a preliminary process, to suppress fluctuations in contrast within the discrimination target image. In the gradation conversion process, degrees of variance of pixel values within local regions of the discrimination target image are caused to approach a predetermined level. The local regions are set to be of a size that includes a single eye of a face to be discriminated.

摘要翻译： 面部鉴别处理基于鉴别目标图像的特征量来判断辨别目标图像是否是脸部的图像。 作为初步处理来施加像素值的灰度变换，以抑制辨别目标图像内的对比度的波动。 在灰度转换处理中，鉴别目标图像的局部区域内的像素值的变化程度达到预定水平。 局部区域被设置为包括要被区别的脸的单个眼睛的尺寸。

公开(公告)号：US20070071353A1

公开(公告)日：2007-03-29

申请号：US11606091

申请日：2006-11-30

申请人： Yoshiro Kitamura ,  Wataru Ito

发明人： Yoshiro Kitamura ,  Wataru Ito

IPC分类号： G06K9/40

CPC分类号： G06K9/40 ,  G06T5/002 ,  G06T5/005 ,  G06T5/20 ,  G06T2207/20012 ,  G06T2207/20192 ,  G06T2207/20224 ,  G06T2207/30196

摘要： A blurred image generating section generates a plurality of blurred images Sm (where m=1 to n and n≧2) different in frequency response characteristic from one another, based on an original image S0. A band-limited image generating section generates a plurality of band-limited images Tm by performing a subtraction between images of adjacent frequency bands, employing the original image S0 and each of the blurred images Sm. A noise component extraction section extracts converted images, obtained by performing nonlinear conversion on each of the band-limited images Tm, as noise components Qm contained in the different frequency bands. A noise-component elimination section subtracts from the original image S0 a value obtained by multiplying a subtraction coefficient β (which is determined according to the pixel value Y0 of the original image S0) and the sum of the noise components Qm together.

摘要翻译： 模糊图像生成部基于原始图像S 0生成彼此的频率响应特性不同的多个模糊图像Sm（其中m = 1到n和n> = 2）。 频带限制图像生成部通过使用原始图像S 0和模糊图像Sm中的每一个执行相邻频带的图像之间的减法来生成多个带限图像Tm。 噪声分量提取部分提取通过对每个频带限制图像Tm执行非线性转换而获得的转换图像作为包含在不同频带中的噪声分量Qm。 噪声分量消除部分从原始图像S 0中减去通过将减法系数β（根据原始图像S 0的像素值Y 0确定）与噪声分量Qm之和相乘得到的值。

公开(公告)号：US20050248655A1

公开(公告)日：2005-11-10

申请号：US11111808

申请日：2005-04-22

申请人： Yoshiro Kitamura ,  Wataru Ito

发明人： Yoshiro Kitamura ,  Wataru Ito

IPC分类号： G06T1/00 ,  G03B17/00 ,  H04N1/393 ,  H04N1/409 ,  H04N5/208 ,  H04N5/232

CPC分类号： H04N5/23248 ,  H04N5/23254 ,  H04N5/23258 ,  H04N5/23264

摘要： High frequency components are efficiently extracted from blurred images, and blur correction is efficiently performed. A blur analyzing means judges whether an image is a blurred image. If the image is judged to be a blurred image, blur data Q, which includes a blur width, is generated and transmitted to a blur correcting means. The blur correcting means extracts high frequency components from the image if the blur width is less than a predetermined threshold value, and performs blur correction by adding the high frequency components to the image. Meanwhile, if the blur width is greater than or equal to the threshold value, a reducing means reduces the size of the image to obtain a reduced image. Then, the blur correcting means extracts high frequency components from the reduced image, and performs blur correction by emphasizing and adding the extracted high frequency components to the reduced image.

摘要翻译： 从模糊图像中有效地提取高频分量，有效地进行模糊校正。 模糊分析装置判断图像是否是模糊图像。 如果图像被判断为模糊图像，则生成包括模糊宽度的模糊数据Q并将其发送到模糊校正装置。 如果模糊宽度小于预定阈值，则模糊校正装置从图像中提取高频分量，并通过将高频分量加到图像上来执行模糊校正。 同时，如果模糊宽度大于或等于阈值，则缩小装置减小图像的尺寸以获得缩小的图像。 然后，模糊校正装置从缩小图像中提取高频分量，并且通过将提取的高频分量强调并添加到缩小图像来执行模糊校正。

公开(公告)号：US20050175247A1

公开(公告)日：2005-08-11

申请号：US11052902

申请日：2005-02-09

申请人： Yoshiro Kitamura ,  Wataru Ito

发明人： Yoshiro Kitamura ,  Wataru Ito

IPC分类号： G06T1/00 ,  G06K9/36 ,  G06K9/40 ,  G06T5/00 ,  G06T5/20 ,  H04N1/387 ,  H04N1/409

CPC分类号： G06K9/40 ,  G06T5/002 ,  G06T5/005 ,  G06T5/20 ,  G06T2207/20012 ,  G06T2207/20192 ,  G06T2207/20224 ,  G06T2207/30196

摘要： A blurred image generating section generates a plurality of blurred images Sm (where m=1 to n and n≧2) different in frequency response characteristic from one another, based on an original image S0. A band-limited image generating section generates a plurality of band-limited images Tm by performing a subtraction between images of adjacent frequency bands, employing the original image S0 and each of the blurred images Sm. A wrinkle component extraction section extracts converted images, obtained by performing nonlinear conversion on each of the band-limited images Tm, as wrinkle components Qm contained in the different frequency bands. A wrinkle-component elimination section eliminates wrinkle components of the original image S0 by subtracting from the original image S0 a value obtained by multiplying a subtraction coefficient β (which is determined according to the pixel value Y0 of the original image S0) and the sum of the wrinkle components Qm together.

摘要翻译： 模糊图像生成部基于原始图像S 0生成彼此的频率响应特性不同的多个模糊图像Sm（其中m = 1到n和n> = 2）。 频带限制图像生成部通过使用原始图像S 0和模糊图像Sm中的每一个执行相邻频带的图像之间的减法来生成多个带限图像Tm。 褶皱成分提取部将通过对各条带限制图像Tm进行非线性变换而得到的转换图像作为不同频带中包含的皱纹成分Qm。 皱纹成分消除部通过从原始图像S 0中减去通过将减法系数β（根据原始图像S 0的像素值Y 0确定的）相乘得到的值来消除原始图像S 0的褶皱成分， 和皱纹成分Qm的总和在一起。

公开(公告)号：US20120076267A1

公开(公告)日：2012-03-29

申请号：US13247379

申请日：2011-09-28

申请人： Takao KUWABARA ,  Wataru Ito ,  Masahiko Yamada ,  Yasunori Ohta ,  Takeshi Kamiya ,  Tetsuro Kusunoki

发明人： Takao KUWABARA ,  Wataru Ito ,  Masahiko Yamada ,  Yasunori Ohta ,  Takeshi Kamiya ,  Tetsuro Kusunoki

IPC分类号： G01N23/04

CPC分类号： A61B6/502 ,  A61B6/5258 ,  A61B6/586

摘要： Disclosed is a technique for correcting a pixel defect in the capture of two radiological images with parallax therebetween. Radiation beam is directly radiated to a radiation detector 15 in two radiographing directions, without passing through a subject, thereby acquiring two defect detecting radiological images. A pixel defect in each of the two defect detecting radiological images is detected in advance. A pixel position where the pixel defect occurs is stored in advance so as to be associated with each radiographing direction. Then, radiation beam is radiated to the subject from the two radiographing directions to acquire two radiological images for diagnosis. A target pixel which is disposed at the stored pixel position where the pixel defect occurs in each of the two radiological images for diagnosis is corrected.

摘要翻译： 公开了一种用于校正捕获两个具有视差的放射性图像的像素缺陷的技术。 辐射光束在两个摄影方向上直接照射到辐射检测器15，而不通过被摄体，从而获得两个缺陷检测放射图像。 预先检测两个缺陷检测放射线图像中的每一个中的像素缺陷。 预先存储像素缺陷发生的像素位置，以便与每个放射照相方向相关联。 然后，辐射束从两个放射照相方向辐射到被摄体，以获得两个用于诊断的放射图像。 校正了在两个用于诊断的放射线图像中的每一个中发生像素缺陷的存储像素位置处的目标像素。

公开(公告)号：US20120051502A1

公开(公告)日：2012-03-01

申请号：US13219529

申请日：2011-08-26

申请人： Yasunori OHTA ,  Wataru Ito ,  Masahiko Yamada ,  Takao Kuwabara ,  Takeshi Kamiya ,  Tetsuro Kusunoki

发明人： Yasunori OHTA ,  Wataru Ito ,  Masahiko Yamada ,  Takao Kuwabara ,  Takeshi Kamiya ,  Tetsuro Kusunoki

IPC分类号： A61B6/04

CPC分类号： A61B6/502 ,  A61B6/00 ,  A61B6/022 ,  A61B6/107 ,  A61B6/405 ,  A61B6/4452 ,  A61B6/4476

摘要： In a mammography system including a face guard, it is possible to prevent a human subject whose head is in close contact with the face guard from losing her posture and being in an unstable state. In a mammography system which includes a shield member for preventing radiation from being irradiated onto the face of the human subject, a radiation source which irradiates radiation is moved, such that, when radiation in two radiographing directions is irradiated from two focal positions distant from the chest wall of the human subject in a forward direction, the shield member is configured to be fixed at a predetermined position in the forward direction without being interlocking with the movement of the radiation source.

摘要翻译： 在包括脸部护理的乳房造影系统中，能够防止头部与脸部护罩紧密接触的人体对象失去其姿势而处于不稳定状态。 在包括用于防止辐射照射到人体对象的遮蔽部件的乳房摄影系统中，照射辐射的辐射源被移动，使得当两个放射线方向上的辐射从远离 人体受试者的前方向的胸壁，屏蔽构件被构造成在向前方向上固定在预定位置，而不与辐射源的移动互锁。

公开(公告)号：US20120306309A1

公开(公告)日：2012-12-06

申请号：US13571584

申请日：2012-08-10

申请人： Masakatsu Matsubara ,  Takashi Hanai ,  Wataru Ito

发明人： Masakatsu Matsubara ,  Takashi Hanai ,  Wataru Ito

IPC分类号： H02K3/28

CPC分类号： H02K3/28

摘要： A stator of rotating electrical machine includes a stator core and stator coils. The stator coils have n number (where n≧6) unit coils, a first coil group and a second coil group. The unit coils of the first coil group include a first unit coil located nearest the first power supply terminal. The unit coils of the first coil group include a second unit coil. The unit coils of the first coil group include a third unit coil located third nearest the first power supply terminal and adjacent to the second unit coil of the second coil group. The unit coils of the second coil group include a third unit coil located third nearest the second power supply terminal and adjacent to the second unit coil of the first coil group.

摘要翻译： 旋转电机的定子包括定子铁芯和定子线圈。 定子线圈具有n个数（n≥6）个单位线圈，第一线圈组和第二线圈组。 第一线圈组的单位线圈包括位于最靠近第一电源端子的第一单元线圈。 第一线圈组的单位线圈包括第二单元线圈。 第一线圈组的单位线圈包括位于第三最接近第一电源端子并且与第二线圈组的第二单元线圈相邻的第三单元线圈。 第二线圈组的单位线圈包括位于第三最接近第二电源端子并与第一线圈组的第二单元线圈相邻的第三单元线圈。