公开(公告)号：US07529787B2

公开(公告)日：2009-05-05

申请号：US11103541

申请日：2005-04-12

申请人： Tetsujiro Kondo ,  Takeshi Miyai ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Yoshiaki Nakamura ,  Takashi Nakanishi ,  Tsugihiko Haga

发明人： Tetsujiro Kondo ,  Takeshi Miyai ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Yoshiaki Nakamura ,  Takashi Nakanishi ,  Tsugihiko Haga

IPC分类号： G06F17/10

CPC分类号： H04N7/0125 ,  H04N7/0145

摘要： A device generates coefficient data of an estimating equation for converting a first information signal to a second information signal. The device performs decimation on a teacher signal to generate a student signal and acquires plural training data items from the teacher signal corresponding to the second information signal and the student signal corresponding to the first information signal. For each training data item, a similarity determination unit acquires the similarity of the student signal with respect to the first information signal corresponding to a second information signal at a position of interest. Coefficient seed data, which are coefficient data of a generation equation including the similarity as a parameter, are determined using the training data items and the similarity. A coefficient data computing unit determines, based on the generation equation, coefficient data of the estimating equation using the coefficient seed data and a similarity value indicating the highest similarity.

摘要翻译： 设备生成用于将第一信息信号转换为第二信息信号的估计方程式的系数数据。 该装置对教师信号执行抽取以生成学生信号，并且从对应于第二信息信号的教师信号和对应于第一信息信号的学生信号获取多个训练数据项。 对于每个训练数据项，相似度确定单元获取学生信号相对于在感兴趣的位置处与第二信息信号相对应的第一信息信号的相似度。 使用训练数据项和相似度来确定作为参数的相似性的生成式的系数数据的系数种子数据。 系数数据计算单元基于生成方程，使用系数种子数据和表示最高相似度的相似度值来确定估计方程式的系数数据。

公开(公告)号：US20050238247A1

公开(公告)日：2005-10-27

申请号：US11110129

申请日：2005-04-20

申请人： Tetsujiro Kondo ,  Shizuo Chikaoka ,  Takeshi Miyai ,  Yoshiaki Nakamura ,  Takashi Nakanishi ,  Tsugihiko Haga ,  Daisuke Kikuchi

发明人： Tetsujiro Kondo ,  Shizuo Chikaoka ,  Takeshi Miyai ,  Yoshiaki Nakamura ,  Takashi Nakanishi ,  Tsugihiko Haga ,  Daisuke Kikuchi

IPC分类号： G06T3/40 ,  G06K9/32 ,  G06K9/40 ,  H04N7/01

CPC分类号： H04N7/0125 ,  H04N7/0145

摘要： A signal processing apparatus includes a generator operable to generate a second image signal by converting a first image signal into the second image signal; a calculation unit operable to calculate a correction amount based on an evaluation of the second image signal relative to the first image signal; and a correction unit operable to correct the second image signal based on the correction amount.

摘要翻译： 信号处理装置包括发生器，其可操作以通过将第一图像信号转换为第二图像信号来产生第二图像信号; 计算单元，其可操作以基于所述第二图像信号相对于所述第一图像信号的评估来计算校正量; 以及校正单元，其可操作以基于所述校正量来校正所述第二图像信号。

公开(公告)号：US07844136B2

公开(公告)日：2010-11-30

申请号：US11564598

申请日：2006-11-29

申请人： Tetsujiro Kondo ,  Takeshi Miyai ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Takashi Nakanishi ,  Yoshiaki Nakamura ,  Tsugihiko Haga

发明人： Tetsujiro Kondo ,  Takeshi Miyai ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Takashi Nakanishi ,  Yoshiaki Nakamura ,  Tsugihiko Haga

IPC分类号： G06K9/32

CPC分类号： H04N7/0135 ,  H04N7/0125 ,  H04N7/0145

摘要： A class configuration generation unit generates (n−1) number of class configurations each of which is comprised of i number of the already selected features plus a feature selected from the remaining (n−i) number of the features (both of n and i are integers). A class configuration selection unit selects an optimal class configuration from the (n−i) number of the class configurations using an arbitrary evaluation value. The features used in the class configuration selected by the selection unit are used as the already selected features in the generation unit. The operations by the generation unit and the selection unit are repeated with values of i sequentially varying from 0 to r−1, thereby generating a class configuration comprised of r number of the features.

摘要翻译： 类配置生成单元生成（n-1）个类配置，每个类配置包括i个已经选择的特征加上从剩余（n-1）个特征（n和i两者）中选择的特征 是整数）。 类配置选择单元使用任意评估值从类别配置的（n-i）个数中选择最佳类配置。 由选择单元选择的类配置中使用的功能用作生成单元中已选择的功能。 按照从0到r-1顺序变化的值重复由生成单元和选择单元的操作，从而生成由r个特征组成的类别配置。

公开(公告)号：US07821572B2

公开(公告)日：2010-10-26

申请号：US10559491

申请日：2004-06-04

申请人： Tetsujiro Kondo ,  Takashi Nakanishi ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Takeshi Miyai ,  Yoshiaki Nakamura ,  Tsugihiko Haga

发明人： Tetsujiro Kondo ,  Takashi Nakanishi ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Takeshi Miyai ,  Yoshiaki Nakamura ,  Tsugihiko Haga

IPC分类号： H04N7/01 ,  H04N11/20

CPC分类号： H04N7/0125 ,  H04N7/0145

摘要： This invention relates to an apparatus for processing an information signal etc. that, when converting, for example, SD signal into HD signal, enables well to be obtained pixel data of HD signal no matter whether the dynamic range DR is large or small. DR in a class tap is detected. If DR≧Th, items of pixel data y1-a−y4-a calculated by using item of coefficient data Wi-a corresponding to a class code Ca are estimated as items of pixel data of HD signal. If DR

摘要翻译： 本发明涉及一种用于处理信息信号等的装置，当将例如SD信号转换为HD信号时，能够很好地获得HD信号的像素数据，无论动态范围DR是大还是小。 检测到类别轻击中的DR。 如果DR≥Th，则通过使用与等级代码Ca对应的系数数据Wi-a的项目计算的像素数据y1-a-y4-a的项目被估计为HD信号的像素数据项。 如果DR

公开(公告)号：US20050246147A1

公开(公告)日：2005-11-03

申请号：US11103541

申请日：2005-04-12

申请人： Tetsujiro Kondo ,  Takeshi Miyai ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Yoshiaki Nakamura ,  Takashi Nakanishi ,  Tsugihiko Haga

发明人： Tetsujiro Kondo ,  Takeshi Miyai ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Yoshiaki Nakamura ,  Takashi Nakanishi ,  Tsugihiko Haga

IPC分类号： H04N7/01 ,  G06F17/10

CPC分类号： H04N7/0125 ,  H04N7/0145

摘要： A device generates coefficient data of an estimating equation for converting a first information signal to a second information signal. The device performs decimation on a teacher signal to generate a student signal and acquires plural training data items from the teacher signal corresponding to the second information signal and the student signal corresponding to the first information signal. For each training data item, a similarity determination unit acquires the similarity of the student signal with respect to the first information signal corresponding to a second information signal at a position of interest. Coefficient seed data, which are coefficient data of a generation equation including the similarity as a parameter, are determined using the training data items and the similarity. A coefficient data computing unit determines, based on the generation equation, coefficient data of the estimating equation using the coefficient seed data and a similarity value indicating the highest similarity.

摘要翻译： 设备生成用于将第一信息信号转换为第二信息信号的估计方程式的系数数据。 该装置对教师信号执行抽取以生成学生信号，并且从对应于第二信息信号的教师信号和对应于第一信息信号的学生信号获取多个训练数据项。 对于每个训练数据项，相似度确定单元获取学生信号相对于在感兴趣的位置处与第二信息信号相对应的第一信息信号的相似度。 使用训练数据项和相似度来确定作为参数的相似性的生成式的系数数据的系数种子数据。 系数数据计算单元基于生成方程，使用系数种子数据和表示最高相似度的相似度值来确定估计方程式的系数数据。

公开(公告)号：US20050201631A1

公开(公告)日：2005-09-15

申请号：US11040586

申请日：2005-01-21

申请人： Tetsujiro Kondo ,  Daisuke Kikuchi ,  Takeshi Miyai ,  Takashi Nakanishi ,  Yoshiaki Nakamura ,  Tsugihiko Haga ,  Shizuo Chikaoka

发明人： Tetsujiro Kondo ,  Daisuke Kikuchi ,  Takeshi Miyai ,  Takashi Nakanishi ,  Yoshiaki Nakamura ,  Tsugihiko Haga ,  Shizuo Chikaoka

IPC分类号： H04N7/01 ,  G06T3/40 ,  G06K9/40

CPC分类号： G06T3/4007

摘要： A pattern matching section compares reference taps supplied by one area extracting section with a reference tap component of a training pair pre-stored in a training-pair storing section, selects a training pair including a reference tap component having highest similarity to the reference taps, and supplies the selected training pair to a normal-equation generating section. Training pairs stored in the training-pair storing section include a SD signal and HD signal. A prediction-coefficient determining section obtains prediction coefficients by solving normal equations generated by the normal-equation generating section. A prediction calculating section produces a HD signal by applying the prediction coefficients to prediction taps extracted by another area extracting section.

摘要翻译： 模式匹配部分将由一个区域提取部分提供的参考抽头与预先存储在训练对存储部分中的训练对的参考抽头分量进行比较，选择包括与参考抽头具有最高相似性的参考抽头分量的训练对， 并将所选择的训练对提供给正态方程生成部。 存储在训练对存储部分中的训练对包括SD信号和HD信号。 预测系数决定部通过求解由正规方程生成部生成的法线方程来求出预测系数。 预测计算部分通过将预测系数应用于由另一区域提取部分提取的预测抽头来产生HD信号。

公开(公告)号：US20050008260A1

公开(公告)日：2005-01-13

申请号：US10852577

申请日：2004-05-25

申请人： Tetsujiro Kondo ,  Takashi Nakanishi ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Takeshi Miyai ,  Yoshiaki Nakamura ,  Tsugihiko Haga

发明人： Tetsujiro Kondo ,  Takashi Nakanishi ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Takeshi Miyai ,  Yoshiaki Nakamura ,  Tsugihiko Haga

IPC分类号： G06K9/32 ,  G06K9/36 ,  H04N7/26 ,  H04N7/28

CPC分类号： H04N19/94 ,  H04N19/98

摘要： Standard Definition signals are divided into blocks at a tap extracting unit, and pixel data contained in each block is extracted as a class tap. A class classification unit obtains class code based on the pixel data contained in the class tap. An auxiliary data generating unit generates auxiliary data regarding conversion into High Definition signals, based on the class tap extracted by the tap extracting unit. A data generation processing unit performs processing based on the class code and the auxiliary data, thereby yielding excellent High Definition signals.

摘要翻译： 标准清晰度信号在抽头提取单元处被划分为块，并且每个块中包含的像素数据被提取为类别抽头。 类分类单元根据包含在类别抽头中的像素数据获得类代码。 辅助数据生成单元基于由抽头提取单元提取的类别抽头，生成关于高清晰度信号的转换的辅助数据。 数据产生处理单元基于类代码和辅助数据执行处理，从而产生优异的高清晰度信号。

公开(公告)号：US07605868B2

公开(公告)日：2009-10-20

申请号：US11040586

申请日：2005-01-21

申请人： Tetsujiro Kondo ,  Daisuke Kikuchi ,  Takeshi Miyai ,  Takashi Nakanishi ,  Yoshiaki Nakamura ,  Tsugihiko Haga ,  Shizuo Chikaoka

发明人： Tetsujiro Kondo ,  Daisuke Kikuchi ,  Takeshi Miyai ,  Takashi Nakanishi ,  Yoshiaki Nakamura ,  Tsugihiko Haga ,  Shizuo Chikaoka

IPC分类号： H04N5/46

CPC分类号： G06T3/4007

摘要： A pattern matching section compares reference taps supplied by one area extracting section with a reference tap component of a training pair pre-stored in a training-pair storing section, selects a training pair including a reference tap component having highest similarity to the reference taps, and supplies the selected training pair to a normal-equation generating section. Training pairs stored in the training-pair storing section include a SD signal and HD signal. A prediction-coefficient determining section obtains prediction coefficients by solving normal equations generated by the normal-equation generating section. A prediction calculating section produces a HD signal by applying the prediction coefficients to prediction taps extracted by another area extracting section.

摘要翻译： 模式匹配部分将由一个区域提取部分提供的参考抽头与预先存储在训练对存储部分中的训练对的参考抽头分量进行比较，选择包括与参考抽头具有最高相似性的参考抽头分量的训练对， 并将所选择的训练对提供给正态方程生成部。 存储在训练对存储部分中的训练对包括SD信号和HD信号。 预测系数决定部通过求解由正规方程生成部生成的法线方程来求出预测系数。 预测计算部分通过将预测系数应用于由另一区域提取部分提取的预测抽头来产生HD信号。

公开(公告)号：US07262808B2

公开(公告)日：2007-08-28

申请号：US10854157

申请日：2004-05-27

申请人： Tetsujiro Kondo ,  Takeshi Miyai ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Takashi Nakanishi ,  Yoshiaki Nakamura ,  Tsugihiko Haga

发明人： Tetsujiro Kondo ,  Takeshi Miyai ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Takashi Nakanishi ,  Yoshiaki Nakamura ,  Tsugihiko Haga

IPC分类号： H04N7/01

CPC分类号： H04N7/0135 ,  H04N7/0125 ,  H04N7/0145

摘要： A class configuration generation unit generates (n−1) number of class configurations each of which is comprised of i number of the already selected features plus a feature selected from the remaining (n−i) number of the features (both of n and i are integers). A class configuration selection unit selects an optimal class configuration from the (n−i) number of the class configurations using an arbitrary evaluation value. The features used in the class configuration selected by the selection unit are used as the already selected features in the generation unit. The operations by the generation unit and the selection unit are repeated with values of i sequentially varying from 0 to r−1, thereby generating a class configuration comprised of r number of the features.

摘要翻译： 类配置生成单元生成（n-1）个类配置，每个类配置包括i个已经选择的特征加上从剩余（ni）个特征中选择的特征（n和i都是整数） ）。 类配置选择单元使用任意评估值从类别配置的（n-i）个数中选择最佳类配置。 由选择单元选择的类配置中使用的功能用作生成单元中已选择的功能。 按照从0到r-1顺序变化的值重复由生成单元和选择单元的操作，从而生成由r个特征组成的类别配置。

公开(公告)号：US20070098269A1

公开(公告)日：2007-05-03

申请号：US11564598

申请日：2006-11-29

申请人： Tetsujiro KONDO ,  Takeshi Miyai ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Takashi Nakanishi ,  Yoshiaki Nakamura ,  Tsugihiko Haga

发明人： Tetsujiro KONDO ,  Takeshi Miyai ,  Daisuke Kikuchi ,  Shizuo Chikaoka ,  Takashi Nakanishi ,  Yoshiaki Nakamura ,  Tsugihiko Haga

IPC分类号： G06K9/62 ,  H04N7/01

CPC分类号： H04N7/0135 ,  H04N7/0125 ,  H04N7/0145

摘要： A class configuration generation unit generates (n−1) number of class configurations each of which is comprised of i number of the already selected features plus a feature selected from the remaining (n−i) number of the features (both of n and i are integers). A class configuration selection unit selects an optimal class configuration from the (n−i) number of the class configurations using an arbitrary evaluation value. The features used in the class configuration selected by the selection unit are used as the already selected features in the generation unit. The operations by the generation unit and the selection unit are repeated with values of i sequentially varying from 0 to r−1, thereby generating a class configuration comprised of r number of the features.

摘要翻译： 类配置生成单元生成（n-1）个类配置，每个类配置包括i个已经选择的特征加上从剩余（ni）个特征中选择的特征（n和i都是整数） ）。 类配置选择单元使用任意评估值从类别配置的（n-i）个数中选择最佳类配置。 由选择单元选择的类配置中使用的功能用作生成单元中已选择的功能。 按照从0到r-1顺序变化的值重复由生成单元和选择单元的操作，从而生成由r个特征组成的类别配置。