专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08836806B2 Image pickup apparatus and image sensor 有权
标题翻译：图像拾取装置和图像传感器
公开(公告)号：US08836806B2
公开(公告)日：2014-09-16
申请号：US13515422
申请日：2010-12-03
申请人： Mie Ishii
发明人： Mie Ishii
IPC分类号： H04N5/225 , H04N9/04 , H04N5/3745 , H04N5/345 , H04N5/369 , H04N5/335 , H04N5/357 , H04N5/353
CPC分类号： H04N9/045 , H04N5/335 , H04N5/3456 , H04N5/3532 , H04N5/3575 , H04N5/3696 , H04N5/37452
摘要： An image pickup apparatus that is capable of taking a distortion-free moving image without enlarging circuit scale. An image sensor has pixels each of which comprises a photoelectric conversion section that generates an electric charge corresponding to the incident light, a charge storage section that stores the electric charge, and an output section that outputs a voltage corresponding to the electric charge. The pixels include a first type pixel with a charge retention section that temporally holds the electric charge before transferring to the charge storage section, and a second type pixel without the charge retention section. A setting unit sets up a mode. A control unit controls to generate an image corresponding the output voltage from the first type pixel in a moving image pickup mode, and to generate an image corresponding to the output voltages from the first and second type pixels in a still image pickup mode.
摘要翻译：能够在不放大电路规模的情况下拍摄无失真运动图像的摄像装置。图像传感器具有像素，每个像素包括产生对应于入射光的电荷的光电转换部分，存储电荷的电荷存储部分和输出与电荷相对应的电压的输出部分。像素包括具有电荷保留部分的第一类型像素，其在传送到电荷存储部分之前暂时保持电荷，以及第二类型像素，而没有电荷保持部分。设置单元设置模式。控制单元控制在运动图像拾取模式中产生对应于来自第一类型像素的输出电压的图像，并且在静止图像拾取模式中产生与来自第一和第二类型像素的输出电压相对应的图像。

2. 发明授权

US08015130B2 Information processing apparatus, information processing method, pattern recognition apparatus, and pattern recognition method 有权
标题翻译：信息处理装置，信息处理方法，模式识别装置和模式识别方法
公开(公告)号：US08015130B2
公开(公告)日：2011-09-06
申请号：US12696993
申请日：2010-01-29
申请人： Masakazu Matsugu , Katsuhiko Mori , Mie Ishii , Yusuke Mitarai
发明人： Masakazu Matsugu , Katsuhiko Mori , Mie Ishii , Yusuke Mitarai
IPC分类号： G06E1/00 , G06E3/00 , G06F15/18 , G06G7/00
CPC分类号： G06K9/4628 , G06K9/00604 , G06N3/049 , G06N3/08
摘要： In a hierarchical neural network having a module structure, learning necessary for detection of a new feature class is executed by a processing module which has not finished learning yet and includes a plurality of neurons which should learn an unlearned feature class and have an undetermined receptor field structure by presenting a predetermined pattern to a data input layer. Thus, a feature class necessary for subject recognition can be learned automatically and efficiently.
摘要翻译：在具有模块结构的分层神经网络中，由尚未完成学习的处理模块执行用于检测新特征类所需的学习，并且包括多个神经元，其应该学习未知的特征类并具有未确定的受体场通过向数据输入层呈现预定图案来构造。因此，可以自动且有效地学习用于对象识别所需的特征类。

3. 发明授权

US07991719B2 Information processing method and apparatus, and image pickup device 有权
标题翻译：信息处理方法和装置以及图像拾取装置
公开(公告)号：US07991719B2
公开(公告)日：2011-08-02
申请号：US11579981
申请日：2005-06-02
申请人： Mie Ishii , Masakazu Matsugu , Katsuhiko Mori , Yusuke Mitarai
发明人： Mie Ishii , Masakazu Matsugu , Katsuhiko Mori , Yusuke Mitarai
IPC分类号： G06N3/00
CPC分类号： G06K9/4628 , G06N3/04 , G06N3/082 , G06T7/12 , G06T2207/20084 , G06T2207/30201
摘要： An output value of neuron within an objective layer of a hierarchical neural network is computed. The data of the output value of neuron is stored in a memory only if the output value of neuron is greater than or equal to a predetermined value by referring to the computed output value of neuron within the objective layer. When the data of the output value of neuron on a former layer of objective layer is read from the memory, the data having a predetermined value is read, instead of the data of the output value of neuron not stored in the memory.
摘要翻译：计算层次神经网络目标层内神经元的输出值。如果神经元的输出值大于或等于预定值，则通过参照计算出的目标层内神经元的输出值，将神经元的输出值的数据存储在存储器中。当从存储器中读取目标层之前的神经元的输出值的数据时，读取具有预定值的数据，而不是未存储在存储器中的神经元的输出值的数据。

4. 发明申请

US20070148679A1 Gene set used for examination of Colon cancer 审中-公开
标题翻译：用于结肠癌检查的基因集
公开(公告)号：US20070148679A1
公开(公告)日：2007-06-28
申请号：US11637087
申请日：2006-12-12
申请人： Mie Ishii , Nobuko Yamamoto , Masahiro Kawaguchi , Tetsuo Okabe , Hiroki Sasaki , Satoshi Yajima , Yasuhiro Matsumura , Hisayuki Matsushita , Hiroyuki Tsunoda , Kunio Harada
发明人： Mie Ishii , Nobuko Yamamoto , Masahiro Kawaguchi , Tetsuo Okabe , Hiroki Sasaki , Satoshi Yajima , Yasuhiro Matsumura , Hisayuki Matsushita , Hiroyuki Tsunoda , Kunio Harada
IPC分类号： C12Q1/68 , C12M1/34
CPC分类号： C12Q1/6886 , C12Q2600/158 , C12Q2600/16
摘要： Colon cancer cells in a sample are screened by analyzing the amount of expression of at least 2 or more genes or products thereof selected from the group of genes listed in Tables 1 and 30. As compared to conventional method, patients having colon cancer can be detected with higher accuracy.
摘要翻译：通过分析选自表1和30中列出的基因组的至少2个或更多个基因或其产物的表达量来筛选样品中的结肠癌细胞。与常规方法相比，可以检测到具有结肠癌的患者精度更高。

5. 发明申请

US20050280711A1 Camera system, camera, and camera control method 有权
标题翻译：相机系统，相机和相机控制方法
公开(公告)号：US20050280711A1
公开(公告)日：2005-12-22
申请号：US11145380
申请日：2005-06-03
申请人： Mie Ishii , Masakazu Matsugu , Katsuhiko Mori , Yusuke Mitarai
发明人： Mie Ishii , Masakazu Matsugu , Katsuhiko Mori , Yusuke Mitarai
IPC分类号： H04N5/225 , G06F17/00 , H04N5/232
CPC分类号： H04N5/232
摘要： Camera information corresponding to the position at which the target to be searched for in the captured image is detected is identified, another camera specified by the identified camera information receives a notification that the target has been detected (S209), and when a notification is received from another camera, the posture of the own camera is controlled so that the area associated with the camera information specifying another camera can be observed (S211).
摘要翻译：识别对应于检测到拍摄图像中要搜索的目标的位置的相机信息，由所识别的相机信息指定的另一相机接收到已经检测到目标的通知（S 209），并且当通知为从另一相机接收，控制自身相机的姿态，使得可以观察到与指定另一相机的相机信息相关联的区域（S 211）。

6. 发明申请

US20050157908A1 Action recognition apparatus and method, moving-object recognition apparatus and method, device control apparatus and method, and program 有权
标题翻译：动作识别装置和方法，移动物体识别装置和方法，装置控制装置和方法以及程序
公开(公告)号：US20050157908A1
公开(公告)日：2005-07-21
申请号：US11035240
申请日：2005-01-13
申请人： Masakazu Matsugu , Katsuhiko Mori , Mie Ishii , Yusuke Mitarai
发明人： Masakazu Matsugu , Katsuhiko Mori , Mie Ishii , Yusuke Mitarai
IPC分类号： G06T1/00 , G03B3/10 , G06K9/00 , G06T7/20
CPC分类号： G06K9/00342 , G06K9/00624 , G06K9/00885
摘要： An action recognition apparatus includes an input unit for inputting image data, a moving-object detection unit for detecting a moving object from the image data, a moving-object identification unit for identifying the detected moving object based on the image data, a state detection unit for detecting a state or an action of the moving object from the image data, and a learning unit for learning the detected state or action by associating the detected state or action with meaning information specific to the identified moving object.
摘要翻译：一种动作识别装置，包括用于输入图像数据的输入单元，用于从图像数据检测移动物体的移动物体检测单元，用于基于图像数据识别检测到的移动物体的移动物体识别单元，状态检测用于从图像数据检测移动物体的状态或动作的单元，以及用于通过将检测到的状态或动作与所识别的移动对象特有的意义信息相关联来学习检测到的状态或动作的学习单元。

7. 发明申请

US20120044390A1 IMAGE CAPTURING APPARATUS AND CONTROL METHOD FOR THE SAME 有权
标题翻译：图像捕获装置及其控制方法
公开(公告)号：US20120044390A1
公开(公告)日：2012-02-23
申请号：US13255923
申请日：2010-03-31
申请人： Mie Ishii
发明人： Mie Ishii
IPC分类号： H04N5/217
CPC分类号： H04N5/3658
摘要： An image capturing apparatus includes an image sensor having an effective pixel area composed of effective pixels that photoelectrically convert an object image and a reference pixel area composed of reference pixels that output pixel signals to be a reference; a first calculation unit that calculates a standard deviation of the pixel signals output from the reference pixel area; a second calculation unit that calculates an integrated value of the pixel signals output from the reference pixel area; a third calculation unit that calculates a correction value for correcting pixel signals output from the effective pixel area, with use of the integrated value; a correction unit that corrects the pixel signals output from the effective pixel area, based on the correction value; and a determination unit that determines whether correction is to be performed by the correction unit, according to the standard deviation.
摘要翻译：图像摄影装置包括：图像传感器，其具有由有效像素构成的有效像素区域，所述有效像素对所述物体图像进行光电转换;以及参考像素区域，所述参考像素区域由输出像素信号的参考像素构成; 第一计算单元，计算从参考像素区域输出的像素信号的标准偏差; 第二计算单元，计算从参考像素区域输出的像素信号的积分值; 第三计算单元，利用积分值计算用于校正从有效像素区域输出的像素信号的校正值; 校正单元，其基于校正值来校正从有效像素区域输出的像素信号; 以及确定单元，其根据标准偏差确定校正单元是否要执行校正。

8. 发明授权

US08094881B2 Action recognition apparatus and method, moving-object recognition apparatus and method, device control apparatus and method, and program 有权
标题翻译：动作识别装置和方法，移动物体识别装置和方法，装置控制装置和方法以及程序
公开(公告)号：US08094881B2
公开(公告)日：2012-01-10
申请号：US11035240
申请日：2005-01-13
申请人： Masakazu Matsugu , Katsuhiko Mori , Mie Ishii , Yusuke Mitarai
发明人： Masakazu Matsugu , Katsuhiko Mori , Mie Ishii , Yusuke Mitarai
IPC分类号： G06K9/00
CPC分类号： G06K9/00342 , G06K9/00624 , G06K9/00885
摘要： An action recognition apparatus includes an input unit for inputting image data, a moving-object detection unit for detecting a moving object from the image data, a moving-object identification unit for identifying the detected moving object based on the image data, a state detection unit for detecting a state or an action of the moving object from the image data, and a learning unit for learning the detected state or action by associating the detected state or action with meaning information specific to the identified moving object.
摘要翻译：一种动作识别装置，包括用于输入图像数据的输入单元，用于从图像数据检测移动物体的移动物体检测单元，用于基于图像数据识别检测到的移动物体的移动物体识别单元，状态检测用于从图像数据检测移动物体的状态或动作的单元，以及用于通过将检测到的状态或动作与所识别的移动对象特有的意义信息相关联来学习检测到的状态或动作的学习单元。

9. 发明授权

US08080381B2 Infectious etiologic agent detection probe and probe set, carrier, and genetic screening method 有权
标题翻译：传染性病原体检测探针和探针组，载体和遗传筛选方法
公开(公告)号：US08080381B2
公开(公告)日：2011-12-20
申请号：US10810550
申请日：2004-03-29
申请人： Nobuko Yamamoto , Masaya Ogura , Masahiro Kawaguchi , Mamoru Tsukada , Hiroto Yoshii , Tomohiro Suzuki , Mie Ishii , Toshifumi Fukui
发明人： Nobuko Yamamoto , Masaya Ogura , Masahiro Kawaguchi , Mamoru Tsukada , Hiroto Yoshii , Tomohiro Suzuki , Mie Ishii , Toshifumi Fukui
IPC分类号： C12Q1/68 , C07H21/04 , C12M1/34
CPC分类号： C12Q1/689 , C12Q1/6837 , Y02A50/451
摘要： An infectious etiologic agent detection probe set which detects an infectious etiologic agent gene, includes a plurality of kinds of probes including oligonucleotide having base sequences selected from each of a plurality of groups selected from a first group including base sequences of SEQ ID Nos. 1 to 14 and complementary sequences thereof, a second group including base sequences of SEQ ID Nos. 15 to 24 and complementary sequences thereof, a third group including base sequences of SEQ ID Nos. 25 to 36 and complementary sequences thereof, a fourth group including base sequences of SEQ ID Nos. 37 to 47 and complementary sequences thereof, a fifth group including base sequences of SEQ ID Nos. 48 to 57 and complementary sequences thereof, a sixth group including base sequences of SEQ ID Nos. 58 to 68 and complementary sequences thereof, a seventh group including base sequences of SEQ ID Nos. 69 to 77 and complementary sequences thereof, an eighth group including base sequences of SEQ ID Nos. 78 to 85 and complementary sequences thereof, a ninth group including base sequences of SEQ ID Nos. 86 to 97 and complementary sequences thereof, and a 10th group including base sequences of SEQ ID Nos. 98 to 106 and complementary sequences thereof.
摘要翻译：检测感染性病原体基因的感染性病原体检测探针组包括多种探针，包括具有选自多个基团中的每一个的碱基序列的寡核苷酸，第一组包括SEQ ID NO.1至 14及其互补序列，第二组包括SEQ ID No.15至24的碱基序列及其互补序列，第三组包括SEQ ID No.25至36的碱基序列及其互补序列，第四组包括碱基序列 SEQ ID No.37至47及其互补序列的第五组，包括SEQ ID No.48至57的碱基序列及其互补序列的第五组，包含SEQ ID No.58至68的碱基序列的第六组及其互补序列第七组，其包括SEQ ID NO：69至77的碱基序列及其互补序列，第八组包括SEQ ID NO：69至77的碱基序列第78至85个及其互补序列，第九组包括SEQ ID No.86-97的碱基序列及其互补序列，以及第十组，其包含SEQ ID NO：98至106的碱基序列及其互补序列。

10. 发明申请

US20100121798A1 INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, PATTERN RECOGNITION APPARATUS, AND PATTERN RECOGNITION METHOD 有权
标题翻译：信息处理装置，信息处理方法，图案识别装置和图案识别方法
公开(公告)号：US20100121798A1
公开(公告)日：2010-05-13
申请号：US12696993
申请日：2010-01-29
申请人： Masakazu Matsugu , Katsuhiko Mori , Mie Ishii , Yusuke Mitarai
发明人： Masakazu Matsugu , Katsuhiko Mori , Mie Ishii , Yusuke Mitarai
IPC分类号： G06N3/08
CPC分类号： G06K9/4628 , G06K9/00604 , G06N3/049 , G06N3/08
摘要： In a hierarchical neural network having a module structure, learning necessary for detection of a new feature class is executed by a processing module which has not finished learning yet and includes a plurality of neurons which should learn an unlearned feature class and have an undetermined receptor field structure by presenting a predetermined pattern to a data input layer. Thus, a feature class necessary for subject recognition can be learned automatically and efficiently.
摘要翻译：在具有模块结构的分层神经网络中，由尚未完成学习的处理模块执行用于检测新特征类所需的学习，并且包括多个神经元，其应该学习未知的特征类并具有未确定的受体场通过向数据输入层呈现预定图案来构造。因此，可以自动且有效地学习用于对象识别所需的特征类。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式