公开(公告)号：US20100080452A1

公开(公告)日：2010-04-01

申请号：US12568122

申请日：2009-09-28

申请人： Takahiro NAGANO ,  Yasuhiro Suto ,  Noriaki Takahashi ,  Tetsujiro Kondo

发明人： Takahiro NAGANO ,  Yasuhiro Suto ,  Noriaki Takahashi ,  Tetsujiro Kondo

IPC分类号： G06K9/62

CPC分类号： H04N7/0125 ,  G06T3/40 ,  H04N7/0145

摘要： A coefficient learning apparatus includes a regression coefficient calculation unit configured to obtain a tap from an image of a first signal; a regression prediction value calculation unit configured to perform a regression prediction computation; a discrimination information assigning unit configured to assign discrimination information to the pixel of interest; a discrimination coefficient calculation unit configured to obtain a tap from the image of the first signal; a discrimination prediction value calculation unit configured to perform a discrimination prediction computation; and a classification unit configured to classify each of the pixels of the image of the first signal into one of the first discrimination class and the second discrimination class. The regression coefficient calculation unit further calculates the regression coefficient using only the pixels classified as the first discrimination class and further calculates the regression coefficient using only the pixel classified as the second discrimination class.

摘要翻译： 系数学习装置包括回归系数计算单元，被配置为从第一信号的图像获得抽头; 回归预测值计算单元，被配置为执行回归预测计算; 鉴别信息分配单元，被配置为向感兴趣的像素分配识别信息; 鉴别系数计算单元，被配置为从所述第一信号的图像获得抽头; 鉴别预测值计算单元，被配置为执行判别预测计算; 以及分类单元，被配置为将第一信号的图像的每个像素分类为第一辨别类别和第二辨别类别中的一个。 回归系数计算单元进一步使用仅被分类为第一鉴别类的像素来计算回归系数，并且仅使用分类为第二鉴别类的像素来计算回归系数。

公开(公告)号：US08401340B2

公开(公告)日：2013-03-19

申请号：US12567146

申请日：2009-09-25

申请人： Takahiro Nagano ,  Yasuhiro Suto ,  Noriaki Takahashi ,  Tetsujiro Kondo

发明人： Takahiro Nagano ,  Yasuhiro Suto ,  Noriaki Takahashi ,  Tetsujiro Kondo

IPC分类号： G06K9/32 ,  H04B1/66 ,  H04N5/765

CPC分类号： H04N7/0125 ,  G06T3/40 ,  H04N7/0145

摘要： An image processing apparatus includes a storage unit in which regression coefficient data is stored for each class on the basis of a tap in which a linear feature amount corresponding to a pixel of interest of first image data and a non-linear feature amount determined from the image data are used as elements; a classification unit configured to classify each of linear feature amounts of a plurality of items of input data of the input first image into a predetermined class; a reading unit configured to read the regression coefficient data; and a data generation unit configured to generate data of a second image obtained by making the first image have higher quality by performing a product-sum computation process by using the regression coefficient data read from the reading unit and elements of the tap of each of the plurality of items of input data of the input first image.

摘要翻译： 一种图像处理装置包括：存储单元，其中，基于与第一图像数据的感兴趣像素对应的线性特征量和从该第一图像数据确定的非线性特征量的线条特征量，对于每个类存储回归系数数据 图像数据用作元素; 分类单元，被配置为将输入的第一图像的多个输入数据项的线性特征量的每一个分类为预定类别; 读取单元，被配置为读取回归系数数据; 以及数据生成单元，被配置为通过使用从读取单元读取的回归系数数据和每个图像的抽头的元素进行乘积和计算处理，生成通过使第一图像具有更高质量而获得的第二图像的数据 输入第一图像的输入数据的多个项目。

公开(公告)号：US20100080451A1

公开(公告)日：2010-04-01

申请号：US12567146

申请日：2009-09-25

申请人： Takahiro Nagano ,  Yasuhiro Suto ,  Noriaki Takahashi ,  Tetsujiro Kondo

发明人： Takahiro Nagano ,  Yasuhiro Suto ,  Noriaki Takahashi ,  Tetsujiro Kondo

IPC分类号： G06K9/62

CPC分类号： H04N7/0125 ,  G06T3/40 ,  H04N7/0145

摘要： An image processing apparatus includes a storage unit in which regression coefficient data is stored for each class on the basis of a tap in which a linear feature amount corresponding to a pixel of interest of first image data and a non-linear feature amount determined from the image data are used as elements; a classification unit configured to classify each of linear feature amounts of a plurality of items of input data of the input first image into a predetermined class; a reading unit configured to read the regression coefficient data; and a data generation unit configured to generate data of a second image obtained by making the first image have higher quality by performing a product-sum computation process by using the regression coefficient data read from the reading unit and elements of the tap of each of the plurality of items of input data of the input first image.

摘要翻译： 一种图像处理装置包括：存储单元，其中，基于与第一图像数据的感兴趣像素对应的线性特征量和从该第一图像数据确定的非线性特征量的线条特征量，对于每个类存储回归系数数据 图像数据用作元素; 分类单元，被配置为将输入的第一图像的多个输入数据项的线性特征量的每一个分类为预定类别; 读取单元，被配置为读取回归系数数据; 以及数据生成单元，被配置为通过使用从读取单元读取的回归系数数据和每个图像的抽头的元素进行乘积和计算处理，生成通过使第一图像具有更高质量而获得的第二图像的数据 输入第一图像的输入数据的多个项目。

公开(公告)号：US08433145B2

公开(公告)日：2013-04-30

申请号：US12568122

申请日：2009-09-28

申请人： Takahiro Nagano ,  Yasuhiro Suto ,  Noriaki Takahashi ,  Tetsujiro Kondo

发明人： Takahiro Nagano ,  Yasuhiro Suto ,  Noriaki Takahashi ,  Tetsujiro Kondo

IPC分类号： G06K9/62

CPC分类号： H04N7/0125 ,  G06T3/40 ,  H04N7/0145

摘要： A coefficient learning apparatus includes a regression coefficient calculation unit configured to obtain a tap from an image of a first signal; a regression prediction value calculation unit configured to perform a regression prediction computation; a discrimination information assigning unit configured to assign discrimination information to the pixel of interest; a discrimination coefficient calculation unit configured to obtain a tap from the image of the first signal; a discrimination prediction value calculation unit configured to perform a discrimination prediction computation; and a classification unit configured to classify each of the pixels of the image of the first signal into one of the first discrimination class and the second discrimination class. The regression coefficient calculation unit further calculates the regression coefficient using only the pixels classified as the first discrimination class and further calculates the regression coefficient using only the pixel classified as the second discrimination class.

摘要翻译： 系数学习装置包括回归系数计算单元，被配置为从第一信号的图像获得抽头; 回归预测值计算单元，被配置为执行回归预测计算; 鉴别信息分配单元，被配置为向感兴趣的像素分配识别信息; 鉴别系数计算单元，被配置为从所述第一信号的图像获得抽头; 鉴别预测值计算单元，被配置为执行判别预测计算; 以及分类单元，被配置为将第一信号的图像的每个像素分类为第一辨别类别和第二辨别类别中的一个。 回归系数计算单元进一步使用仅被分类为第一鉴别类的像素来计算回归系数，并且仅使用分类为第二鉴别类的像素来计算回归系数。

公开(公告)号：US07068845B2

公开(公告)日：2006-06-27

申请号：US09779139

申请日：2001-02-08

申请人： Tetsujiro Kondo ,  Hideo Nakaya ,  Tsutomu Watanabe ,  Hideki Ohtsuka ,  Yasuaki Takahashi ,  Seiji Wada ,  Takahiro Nagano ,  Koji Ohta ,  Hisakazu Shiraki

发明人： Tetsujiro Kondo ,  Hideo Nakaya ,  Tsutomu Watanabe ,  Hideki Ohtsuka ,  Yasuaki Takahashi ,  Seiji Wada ,  Takahiro Nagano ,  Koji Ohta ,  Hisakazu Shiraki

IPC分类号： G06K3/62

CPC分类号： H04N19/587 ,  H04N19/89 ,  H04N19/895

摘要： A class synthesizing circuit classifies an aimed-at data item into one of a plurality of classes specified in advance, according to a plurality of data items disposed around the aimed-at data item. A coefficient holding and class-code selection circuit stores conversion information for the aimed-at data item, for each class. An estimation-prediction calculation circuit converts the aimed-at data item to a higher-quality data item according to the conversion information. The class synthesizing circuit classifies the aimed-at data item into a different class according to whether the aimed-at data item is missing.

公开(公告)号：US07684635B2

公开(公告)日：2010-03-23

申请号：US10562176

申请日：2004-06-15

申请人： Tetsujiro Kondo ,  Tetsushi Kokubo ,  Kazushi Yoshikawa ,  Hisakazu Shiraki ,  Michimasa Obana ,  Hideo Kasama ,  Masanori Kanemaru

发明人： Tetsujiro Kondo ,  Tetsushi Kokubo ,  Kazushi Yoshikawa ,  Hisakazu Shiraki ,  Michimasa Obana ,  Hideo Kasama ,  Masanori Kanemaru

IPC分类号： G06K9/40 ,  G06K9/48 ,  H04N5/228

CPC分类号： G06K9/4609 ,  G06T1/00 ,  G06T5/003 ,  G06T2207/20201

摘要： A signal processing device and signal processing method, and program and recording medium, whereby images and the like closer approximating real world signals can be obtained. An object which is moving at a movement amount v in the horizontal direction is photographed, and an image wherein the object is blurred is input into a signal processing device. A continuity setting unit supplies the movement amount v of the object to an actual world estimating unit as continuity information. The actual world estimating unit estimates a pixel value for an image without blurring, by computing a normal equation comprising a model equation which models the relation of the pixel values in the input image and the pixel values in an image without blurring according to the movement amount v, and a constraint condition expression which constrains between the pixels in an image without blurring, and supplies this to an image generating unit. The present invention can be applied to, for example, cases of removing movement blurring from an image, for example.

摘要翻译： 信号处理装置和信号处理方法以及程序和记录介质，从而可以获得近似于真实世界信号的图像等。 拍摄以水平方向移动量v的物体，并将其中物体模糊的图像输入信号处理装置。 连续性设置单元将对象的移动量v作为连续性信息提供给实际世界估计单元。 实际世界估计单元通过计算包含模型方程式的正规方程来估计图像的像素值，该模型方程式根据移动量模拟输入图像中的像素值与图像中的像素值而不模糊 v，以及限制图像中的像素之间的模糊的约束条件表达式，并将其提供给图像生成单元。 例如，本发明可以应用于例如从图像中去除运动模糊的情况。

公开(公告)号：US07512285B2

公开(公告)日：2009-03-31

申请号：US11626556

申请日：2007-01-24

申请人： Tetsujiro Kondo ,  Tetsushi Kokubo ,  Kazushi Yoshikawa ,  Hisakazu Shiraki ,  Michimasa Obana ,  Hideo Kasama ,  Masanori Kanemaru

发明人： Tetsujiro Kondo ,  Tetsushi Kokubo ,  Kazushi Yoshikawa ,  Hisakazu Shiraki ,  Michimasa Obana ,  Hideo Kasama ,  Masanori Kanemaru

IPC分类号： G06K9/40 ,  H04N5/228

CPC分类号： G06K9/4609 ,  G06T1/00 ,  G06T5/003 ,  G06T2207/20201

摘要： A signal processing device, signal processing method, and program and recording medium which provide images and the like closer approximating real world signals. The signal processing device includes a processing region setting unit, a movement vector setting unit, a model generator, a normal equation generator, an activity detector, a weighting change unit, and a real world estimating unit.

摘要翻译： 信号处理装置，信号处理方法以及程序和记录介质，其提供近似于真实世界信号的图像等。 信号处理装置包括处理区域设定单元，移动矢量设定单元，模型生成器，正规方程生成器，活动检测器，加权变更单元，以及真实世界估计单元。

公开(公告)号：US07499895B2

公开(公告)日：2009-03-03

申请号：US10475361

申请日：2002-02-21

申请人： Tetsujiro Kondo ,  Kazushi Yoshikawa ,  Tetsushi Kokubo ,  Hisakazu Shiraki ,  Michimasa Obana ,  Hideo Kasama ,  Masanori Kanemaru

发明人： Tetsujiro Kondo ,  Kazushi Yoshikawa ,  Tetsushi Kokubo ,  Hisakazu Shiraki ,  Michimasa Obana ,  Hideo Kasama ,  Masanori Kanemaru

IPC分类号： G06F17/00 ,  G06N5/00

CPC分类号： G06T1/00 ,  G06T5/00 ,  G06T2207/20081

摘要： A signal processing device for learning operations made by a user, and for generating signal optimal to the user based on the learning results. A learning unit monitors supplied operating signals generated based on user operations, and judges whether to learn the operating signals. When the operating signals are to be learned, the learning unit learns a correction norm for correcting input signals, based on the learning operating signals and outputs the correction norm to a correcting unit. The correcting unit corrects input signals based on the correction norm and outputs the corrected signals as output signals. The present invention can be applied to an NR (Noise Reduction) circuit which removes noise.

摘要翻译： 一种信号处理装置，用于由用户进行的学习操作，并且用于基于学习结果产生对用户最佳的信号。 学习单元监视基于用户操作生成的所提供的操作信号，并且判断是否学习操作信号。 当要学习操作信号时，学习单元基于学习操作信号学习用于校正输入信号的校正范数，并将校正范数输出到校正单元。 校正单元基于校正范数校正输入信号，并输出校正后的信号作为输出信号。 本发明可以应用于消除噪声的NR（降噪）电路。

公开(公告)号：US20070115286A1

公开(公告)日：2007-05-24

申请号：US11626439

申请日：2007-01-24

申请人： Tetsujiro Kondo ,  Kazushi Yoshikawa ,  Tetsushi Kokubo ,  Hisakazu Shiraki ,  Michimasa Obana ,  Masanori Kanemaru ,  Hideo Kasama

发明人： Tetsujiro Kondo ,  Kazushi Yoshikawa ,  Tetsushi Kokubo ,  Hisakazu Shiraki ,  Michimasa Obana ,  Masanori Kanemaru ,  Hideo Kasama

IPC分类号： G06T15/50

CPC分类号： G06T3/4023 ,  G06K9/4609 ,  G06T5/003

摘要： A signal processing device, signal processing method, and program and recording medium which provide images and the like closer approximating real world signals. The signal processing device includes a processing region setting unit, a motion vector setting unit, a model generator, a normal equation generator, a weighting change unit, and a real world estimating unit.

摘要翻译： 信号处理装置，信号处理方法以及程序和记录介质，其提供近似于真实世界信号的图像等。 信号处理装置包括处理区域设定单元，运动矢量设定单元，模型生成器，正规方程生成器，加权改变单元，以及真实世界估计单元。

公开(公告)号：US07085318B2

公开(公告)日：2006-08-01

申请号：US10049553

申请日：2001-06-15

申请人： Tetsujiro Kondo ,  Hisakazu Shiraki ,  Yasunobu Node ,  Katsuhisa Shinmei

发明人： Tetsujiro Kondo ,  Hisakazu Shiraki ,  Yasunobu Node ,  Katsuhisa Shinmei

IPC分类号： H04N7/12

CPC分类号： H04N7/0125 ,  H04N5/21 ,  H04N19/117 ,  H04N19/137 ,  H04N19/59 ,  H04N19/98

摘要： A picture processing apparatus for generating an output picture signal with higher quality than the input picture signal. A first signal processor has a storage device for storing a picture signal with the same quality as the output picture signal. The input picture signal and the stored picture signal are added to generate a first picture signal with higher quality than the input picture, which is stored in the storage device. A second signal processor performs a class categorizing adaptive process by extracting a feature of the input picture signal corresponding to the position of a considered pixel of the output picture signal, categorizing the considered pixel as one of a plurality of classes corresponding to the feature, and calculating the input picture signal using a predetermined calculating method corresponding to the categorized class, thereby generating a second picture signal with higher quality than the input picture signal. One of the first and second picture signals is selected as the output picture signal.

摘要翻译： 一种图像处理装置，用于产生质量高于输入图像信号的输出图像信号。 第一信号处理器具有用于存储与输出图像信号具有相同质量的图像信号的存储装置。 添加输入图像信号和存储的图像信号以产生比存储在存储装置中的输入图像更高质量的第一图像信号。 第二信号处理器通过提取与输出图像信号的所考虑的像素的位置相对应的输入图像信号的特征来执行类分类自适应处理，将所考虑的像素分类为与特征对应的多个类别之一，以及 使用对应于分类的预定计算方法计算输入图像信号，从而生成质量高于输入图像信号的第二图像信号。 选择第一和第二图像信号之一作为输出图像信号。