公开(公告)号：US09230155B2

公开(公告)日：2016-01-05

申请号：US13551285

申请日：2012-07-17

申请人： Manabu Yamazoe

发明人： Manabu Yamazoe

IPC分类号： G06K9/00 ,  G06K9/03

CPC分类号： G06K9/00228 ,  G06K9/00751 ,  G06K9/036

摘要： An image processing apparatus according to the present invention can specify, among a plurality of frames, a plurality of frame groups having at least one frame included between the plurality of frame groups that are extraction target candidates in an array of the plurality of frames in the moving image according to a predetermined frame interval, analyze each of the plurality of specified frame groups, and extract a frame to be output from each of the plurality of frame groups based on a result of the analysis.

摘要翻译： 根据本发明的图像处理装置可以在多个帧中指定多个帧组，其具有包括在多个帧组中的至少一个帧，这些帧是在多个帧中的多个帧的阵列中的提取目标候选 根据预定的帧间隔对运动图像进行分析，分析多个指定帧组中的每一个，并且基于分析结果从多个帧组中的每一个提取要输出的帧。

公开(公告)号：US09202284B2

公开(公告)日：2015-12-01

申请号：US13178978

申请日：2011-07-08

申请人： Yuji Akiyama ,  Naoki Sumi ,  Manabu Yamazoe ,  Yoshinori Kawai

发明人： Yuji Akiyama ,  Naoki Sumi ,  Manabu Yamazoe ,  Yoshinori Kawai

IPC分类号： G06K9/00 ,  G06K9/36 ,  G06K9/46 ,  G06T7/20 ,  H04N19/51

CPC分类号： G06T7/2033 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/20164 ,  H04N19/51

摘要： An apparatus includes an extraction unit to extract a feature point in a first image. A determination unit determines a motion vector that corresponds to the feature point extracted from the first image by the extraction unit and a corresponding point that is located in a second image and that has a highest degree of similarity between image data for the feature point and image data for the corresponding point, among candidates of the corresponding point in the second image. A correction unit corrects a first motion vector determined by the determination unit by employing a second motion vector determined by the determination unit. The correction unit employs the second motion vector, in accordance with both of a first degree of similarity between the feature point and the corresponding point, and a second degree of similarity between the feature point and another candidate among the candidates.

摘要翻译： 一种装置，包括提取单元，用于提取第一图像中的特征点。 确定单元通过提取单元确定与从第一图像提取的特征点相对应的运动矢量和位于第二图像中的对应点，并且对于特征点和图像的图像数据之间具有最高相似度 相应点的数据，在第二个图像中的对应点的候选中。 校正单元通过采用由确定单元确定的第二运动矢量校正由确定单元确定的第一运动矢量。 校正单元根据特征点和对应点之间的第一相似度两者以及候选中的特征点与另一个候选者之间的第二相似度二者来应用第二运动矢量。

公开(公告)号：US08256866B2

公开(公告)日：2012-09-04

申请号：US12868155

申请日：2010-08-25

申请人： Akiko Maru ,  Manabu Yamazoe ,  Satoshi Seki ,  Mitsuhiro Ono ,  Atsuhiko Masuyama ,  Hiroshi Tajika

发明人： Akiko Maru ,  Manabu Yamazoe ,  Satoshi Seki ,  Mitsuhiro Ono ,  Atsuhiko Masuyama ,  Hiroshi Tajika

IPC分类号： B41J29/38

CPC分类号： B41J29/02 ,  B41J3/60 ,  B41J29/38

摘要： There is provided an ink jet recording apparatus capable of shortening the recording duration even when an image to be recorded includes a high-duty area having a large amount of ink to be discharged in the case of two-sided recording on a recording medium. The ink jet recording apparatus, which reverses the recording medium to enable two-sided recording, performs dividing the image to be recorded on a high-duty area having a large amount of ink to be discharged into two (first and second) planes, first plane recording involving a unit area to be subjected to an ink discharge amount below a predetermined amount, reversing the recording medium, and recording on the rear surface, and reversing the recording medium again, and second plane recording.

摘要翻译： 提供了一种能够缩短记录持续时间的喷墨记录装置，即使在要记录的图像包括在记录介质上进行双面记录的情况下要排出的具有大量墨水的高占空比区域。 首先将记录介质反转以进行双面记录的喷墨记录装置将要记录在具有大量墨水的高占空比区域中的图像分割成第一和第二平面 平面记录涉及要使墨水排出量低于预定量的单位面积，反转记录介质，并在后表面上记录，以及再次反转记录介质和第二平面记录。

公开(公告)号：US20120014606A1

公开(公告)日：2012-01-19

申请号：US13167864

申请日：2011-06-24

申请人： Manabu Yamazoe ,  Naoki Sumi

发明人： Manabu Yamazoe ,  Naoki Sumi

IPC分类号： G06K9/46

CPC分类号： G06K9/481 ,  G06T7/251

摘要： To improve the precision of a motion vector of a pixel included in an image by appropriately performing region division of the image. A plurality of images is obtained, any of the plurality of the obtained images is analyzed and a feature point of the image is extracted. A feature point of the image are added to the corners of the image and at least one feature point is added to any of positions on four sides formed by the feature points located at the corners of the image. Then, based on the extracted feature point and the added feature points, a motion vector of a pixel included in the image with respect to another image included in the plurality of images is determined.

摘要翻译： 通过适当地执行图像的区域分割来提高图像中包括的像素的运动矢量的精度。 获得多个图像，分析所获得的多个图像中的任何一个，并且提取图像的特征点。 图像的特征点被添加到图像的角部，并且至少一个特征点被添加到由位于图像的角部的特征点形成的四个侧面上的任何位置。 然后，基于所提取的特征点和附加的特征点，确定包括在图像中的相对于包括在多个图像中的另一图像的像素的运动矢量。

公开(公告)号：US07885459B2

公开(公告)日：2011-02-08

申请号：US12210458

申请日：2008-09-15

申请人： Manabu Yamazoe ,  Kentaro Yano

发明人： Manabu Yamazoe ,  Kentaro Yano

IPC分类号： G06K9/00

CPC分类号： G06T5/009 ,  G06T2207/10024 ,  H04N1/6077

摘要： An image processing method includes sampling image data of an original image, analyzing an image that includes the image data sampled in the sampling step, based on luminance and color components of the image data, determining a rotation matrix for a color balance correction based on an analysis result obtained in the analyzing step, and executing the color balance correction on the image data of the original image, based on the determined rotation matrix.

摘要翻译： 一种图像处理方法，包括对原始图像的图像数据进行采样，基于图像数据的亮度和颜色分量来分析包括在采样步骤中采样的图像数据的图像，基于图像数据确定色彩平衡校正的旋转矩阵 在分析步骤中获得的分析结果，并且基于所确定的旋转矩阵对原始图像的图像数据执行颜色平衡校正。

公开(公告)号：US20090161917A1

公开(公告)日：2009-06-25

申请号：US12340031

申请日：2008-12-19

申请人： Ayumi Hori ,  Hidetsugu Kagawa ,  Fumihiro Goto ,  Manabu Yamazoe ,  Maya Ishii ,  Tohru Ikeda

发明人： Ayumi Hori ,  Hidetsugu Kagawa ,  Fumihiro Goto ,  Manabu Yamazoe ,  Maya Ishii ,  Tohru Ikeda

IPC分类号： G06K9/00

CPC分类号： G06K9/00 ,  G10G1/00

摘要： A sheet music processing method of processing, by an image processing apparatus, image data of sheet music input by an input device, the method comprising setting, by a user using a designation unit of the image processing apparatus, a unit in which the image data of the sheet music is processed; dividing the image data of the sheet music into units corresponding to the unit; determining whether image data of a first one of the units is repeated in one or more others of the units; and processing the image data, when the image data of the first one of the units is determined to be repeated in the one or more others of the units, to append information using the image processing apparatus to the image data of the first one of the units and the image data of the one or more others of the units.

摘要翻译： 一种由图像处理装置处理由输入装置输入的乐谱的图像数据的乐谱处理方法，所述方法包括由用户使用所述图像处理装置的指定单元设置其中所述图像数据 的乐谱被处理; 将乐谱的图像数据分割成与单元对应的单位; 确定所述单元中的第一单元的图像数据是否在所述单元的一个或多个其他单元中重复; 以及处理所述图像数据，当所述单元中的所述一个或多个单元中确定要重复所述单元中的所述第一单元的图像数据时，使用所述图像处理设备将信息附加到所述图像数据的第一个的图像数据 单位和单位的一个或多个其他单位的图像数据。

公开(公告)号：US20090158915A1

公开(公告)日：2009-06-25

申请号：US12335330

申请日：2008-12-15

申请人： Maya Ishii ,  Fumihiro Goto ,  Ayumi Hori ,  Manabu Yamazoe ,  Tohru Ikeda ,  Hidetsugu Kagawa

发明人： Maya Ishii ,  Fumihiro Goto ,  Ayumi Hori ,  Manabu Yamazoe ,  Tohru Ikeda ,  Hidetsugu Kagawa

IPC分类号： G09B15/02 ,  H04N1/04

CPC分类号： G09B15/02 ,  H04N1/00795 ,  H04N1/00801 ,  H04N1/00822 ,  H04N1/00827 ,  H04N1/2307 ,  H04N1/233 ,  H04N1/2369 ,  H04N1/2384 ,  H04N1/3872

摘要： Image data of sheet music formed from a plurality of pages is input, and the input image data is divided into bars. The complexity of performance of each divided bar is determined for each page. An easy-to-play portion is detected as a page feed position for each page in accordance with the determination result. The layout of the sheet music is changed based on the detected page feed position, and the layout-changed sheet music is output.

摘要翻译： 输入从多页形成的乐谱的图像数据，将输入图像数据分割成条。 确定每个分页栏的性能的复杂性。 根据确定结果，检测到每个页面的页面馈送位置的易于播放的部分。 基于检测到的页面馈送位置改变乐谱的布局，并输出布局改变的乐谱。

公开(公告)号：US07515294B2

公开(公告)日：2009-04-07

申请号：US10761612

申请日：2004-01-21

申请人： Manabu Yamazoe ,  Makoto Torigoe ,  Shigeru Mizoguchi ,  Yuji Akiyama ,  Ryosuke Iguchi ,  Takashi Fujita

发明人： Manabu Yamazoe ,  Makoto Torigoe ,  Shigeru Mizoguchi ,  Yuji Akiyama ,  Ryosuke Iguchi ,  Takashi Fujita

IPC分类号： G06K15/00

CPC分类号： H04N1/00413 ,  G06F17/3028 ,  H04N1/00132 ,  H04N1/00196 ,  H04N1/0044 ,  H04N1/00458 ,  H04N5/781 ,  H04N21/4316 ,  H04N21/47

摘要： An image extracting method that can efficiently extract a predetermined number of images from a large amount of image data and improve user operability. Evaluations for a plurality of images are input. A predetermined number of images are extracted from the plurality of images based on the input evaluations. In a preferred form, the evaluations are sequentially input for respective ones of the plurality of images, preferably, in chronological order.

摘要翻译： 一种能够从大量图像数据有效地提取预定数量的图像并提高用户可操作性的图像提取方法。 输入多个图像的评价。 基于输入的评价，从多个图像中提取预定数量的图像。 在优选形式中，优选地以时间顺序对相应的多个图像中的相应图像依次输入评估。

公开(公告)号：US07414754B2

公开(公告)日：2008-08-19

申请号：US10938603

申请日：2004-09-13

申请人： Manabu Yamazoe

发明人： Manabu Yamazoe

IPC分类号： G06K15/00 ,  G06F13/00

CPC分类号： H04N1/6033

摘要： A method of easily obtaining a color conversion matrix serving as a foundation of color reproduction at a high speed irrespective of its degree is provided. The method has: a step of constructing nth-degree matrix coefficients regarding a first color space of a plurality of color patch data sets and obtaining a pseudo inverse matrix to the obtained matrix; and a step of forming a color conversion matrix from a product of a matrix constructed by color data regarding a second color space of the color patch data sets and the pseudo inverse matrix.

摘要翻译： 提供一种容易地获得作为色彩再现的基础的色彩转换矩阵，而不管其程度如何，以高速度。 该方法具有以下步骤：构建关于多个色块数据集的第一颜色空间的第n次矩阵系数，并获得所获得的矩阵的伪逆矩阵; 以及从颜色数据构成的矩阵的乘积形成关于色块数据集的第二颜色空间和伪逆矩阵的步骤。

公开(公告)号：US07190830B2

公开(公告)日：2007-03-13

申请号：US10629637

申请日：2003-07-30

申请人： Manabu Yamazoe ,  Kentaro Yano

发明人： Manabu Yamazoe ,  Kentaro Yano

IPC分类号： G06K9/00

CPC分类号： G06T5/009 ,  G06T2207/10024 ,  H04N1/6077

摘要： Correction for color fog is securely achieved with limited load of processing. The RGB image data are converted into the luminance Y and the chromaticity values C1, C2, then a highlight point and a shadow point are determined and are connected to define the axis of the color solid. The color solid is rotated so as that the axis becomes parallel to the luminance axis Y and is so translated in parallel manner that the pixel of the minimum luminance coincides with the original point of the color space.

摘要翻译： 通过加工的有限负载可靠地实现色雾校正。 将RGB图像数据转换成亮度Y和色度值C 1，C 2，然后确定高光点和阴影点并连接以定义色彩固体的轴。 颜色固体被旋转，使得轴变得平行于亮度轴Y，并且平行地平移，使得最小亮度的像素与颜色空间的原始点一致。