会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明授权
    • Techniques to suppress noises in an image to precisely extract shapes and edges
    • 抑制图像噪声以精确提取形状和边缘的技术
    • US09092870B2
    • 2015-07-28
    • US13061270
    • 2009-08-28
    • Nao MishimaKenzo IsogawaRyusuke HiraiGoh Itoh
    • Nao MishimaKenzo IsogawaRyusuke HiraiGoh Itoh
    • G09G5/00G06T7/00
    • G06T7/0085G06T7/13
    • An image processing apparatus includes an operating unit configured to calculate a tangent-line direction of an edge and a normal-line direction of the edge by using a vertical-direction derivative value and a horizontal-direction derivative value of a pixel value of a pixel in an input image; a converting unit configured to convert local coordinates positioned within a predetermined area with respect to a target pixel in the input image into rotated coordinates, by rotating the local coordinates according to an angle formed by the horizontal direction and the tangent-line direction of the edge; and a fitting unit configured to perform, at the rotated coordinates, a fitting process that employs a least-squares method by using a curved surface model expressed with the pixel value of the target pixel in the input image.
    • 一种图像处理装置,包括:操作单元,被配置为通过使用垂直方向导数值和像素的像素值的水平方向导数值来计算边缘的切线方向和边缘的法线方向 在输入图像中; 转换单元,被配置为通过根据由水平方向和边缘的切线方向形成的角度旋转局部坐标,将位于输入图像中的目标像素的预定区域内的局部坐标转换为旋转坐标 ; 以及装配单元,被配置为在旋转的坐标处执行使用通过使用由输入图像中的目标像素的像素值表示的曲面模型而采用最小二乘法的拟合处理。
    • 2. 发明申请
    • Apparatus, Method, and Computer Program Product for Generating Interpolated Images
    • 用于生成内插图像的装置,方法和计算机程序产品
    • US20090244389A1
    • 2009-10-01
    • US12408424
    • 2009-03-20
    • Nao MishimaRyusuke HiraiYasutoyo TakeyamaGoh Itoh
    • Nao MishimaRyusuke HiraiYasutoyo TakeyamaGoh Itoh
    • H04N5/14G06K9/32
    • H04N5/144G06T3/4007H04N19/117H04N19/132H04N19/139H04N19/51H04N19/521H04N19/527H04N19/577H04N19/587
    • An interpolated image generating apparatus calculates a motion vector reliability level indicating reliability of a motion vector used for inserting an interpolated image, the value of the motion vector reliability level being determined in such a manner that the stronger the correlation is between a source image area and a destination image area that are brought into correspondence with each other by the motion vector, the larger is the value. The apparatus also calculates a failure-preventing vector reliability level indicating reliability of a predetermined failure-preventing vector used for preventing image failures. The apparatus obtains a motion compensated image based on the motion vector, obtains a failure-preventing image based on the failure-preventing vector, and blends the motion compensated image and the failure-preventing image according to a weighted average thereof calculated by using a weighting factor based on the motion vector reliability level and the failure-preventing vector reliability level.
    • 内插图像生成装置计算表示用于插入内插图像的运动矢量的可靠性的运动矢量可靠度水平,运动矢量可靠性水平的值被确定为使源图像区域和源图像区域之间的相关性越强 通过运动矢量相互对应的目的地图像区域的值越大。 该装置还计算表示用于防止图像故障的预定故障防止向量的可靠性的防故障向量可靠性水平。 该装置基于运动矢量获得运动补偿图像,基于防故障向量获得防故障图像,并且根据通过使用加权来计算的加权平均值来混合运动补偿图像和防故障图像 基于运动矢量可靠度水平和防故障矢量可靠性水平的因子。
    • 3. 发明申请
    • MOTION VECTOR DETECTION METHOD AND APPARATUS
    • 运动矢量检测方法和装置
    • US20070153903A1
    • 2007-07-05
    • US11686457
    • 2007-03-15
    • Goh ItohNao MishimaHaruhiko Okumura
    • Goh ItohNao MishimaHaruhiko Okumura
    • H04N11/02H04N11/04
    • H04N5/145H04N19/51H04N19/521H04N19/533H04N19/573H04N19/577
    • A motion vector detection method includes extracting a first block from the m-th picture, extracting second blocks having a large correlation with respect to the first block from a (m+n)-th picture ((m+n)>m-th), detecting first motion vectors between the first and second blocks, extracting a third block located in spatially the same position as that of the first block from a (m+i)-th picture ((m+n)>(m+i)>m-th), computing second motion vectors of (n−1)/n times the first motion vectors, extracting a fourth block corresponding to a movement position of the third block from the (m+n)-th picture according to the second motion vector, and selecting an optimum motion vector maximizing a correlation between the third and fourth blocks from the first motion vectors.
    • 运动矢量检测方法包括从第m图像中提取第一块,从第(m + n)个图像((m + n)> m-th)提取相对于第一块具有较大相关性的第二块 ),检测第一和第二块之间的第一运动矢量,从第(m + i)个图像((m + n)>(m + i)>(m + i))中提取位于空间上与第一块相同位置的第三块 )m),计算第一运动矢量的第(n-1)/ n倍的第二运动矢量,根据第(m + n)个图像提取与第三块的移动位置相对应的第四块 并且从所述第一运动矢量中选择最大化所述第三和第四块之间的相关性的最佳运动矢量。
    • 5. 发明授权
    • Motion vector detection method and apparatus
    • 运动矢量检测方法及装置
    • US08144777B2
    • 2012-03-27
    • US11686457
    • 2007-03-15
    • Goh ItohNao MishimaHaruhiko Okumura
    • Goh ItohNao MishimaHaruhiko Okumura
    • H04N7/12H04N11/02H04N11/04
    • H04N5/145H04N19/51H04N19/521H04N19/533H04N19/573H04N19/577
    • A motion vector detection method includes extracting a first block from the m-th picture, extracting second blocks having a large correlation with respect to the first block from a (m+n)-th picture ((m+n)>m-th), detecting first motion vectors between the first and second blocks, extracting a third block located in spatially the same position as that of the first block from a (m+i)-th picture ((m+n)>(m+i)>m-th), computing second motion vectors of (n−1)/n times the first motion vectors, extracting a fourth block corresponding to a movement position of the third block from the (m+n)-th picture according to the second motion vector, and selecting an optimum motion vector maximizing a correlation between the third and fourth blocks from the first motion vectors.
    • 运动矢量检测方法包括从第m图像中提取第一块,从第(m + n)个图像((m + n)> m-th)提取相对于第一块具有较大相关性的第二块 ),检测第一和第二块之间的第一运动矢量,从第(m + i)个图像((m + n)>(m + i)>(m + i))中提取位于空间上与第一块相同位置的第三块 )m),计算第一运动矢量的第(n-1)/ n倍的第二运动矢量,根据第(m + n)个图像提取与第三块的移动位置相对应的第四块 并且从所述第一运动矢量中选择最大化所述第三和第四块之间的相关性的最佳运动矢量。
    • 6. 发明授权
    • Motion estimation apparatus and method
    • 运动估计装置及方法
    • US08019123B2
    • 2011-09-13
    • US12048887
    • 2008-03-14
    • Nao MishimaGoh Itoh
    • Nao MishimaGoh Itoh
    • G06K9/00
    • G06T7/238
    • An estimation unit calculates an estimated motion vector between a first source region of a plurality of source regions and a first destination region on a destination picture. The first destination region has the highest correlation with the first source region. A weight calculation unit searches a plurality of second destination regions. Each second destination region is pointed by the estimated motion vector of another source region adjacent to the first source region. The weight calculation unit extracts pixel values of each second destination region, calculates a difference of pixel values between the first source region and each second destination region, and calculates a weight based on the difference. The weight is smaller if the difference is larger. A filtering unit calculates a motion vector of the first source region by averaging the estimated motion vectors with the weight.
    • 估计单元计算多个源区域的第一源区域和目的地图像上的第一目的地区域之间的估计运动矢量。 第一目的地区域与第一源区域的相关性最高。 权重计算单元搜索多个第二目的地区域。 每个第二目的地区域由与第一源区域相邻的另一源区域的估计的运动矢量指向。 权重计算单元提取每个第二目的地区域的像素值,计算第一源区域和每个第二目的地区域之间的像素值的差异,并且基于该差异来计算权重。 如果差值较大,重量较小。 滤波单元通过对具有权重的估计运动矢量进行平均来计算第一源区域的运动矢量。
    • 7. 发明授权
    • Method, apparatus and computer program product for generating interpolation frame
    • 用于生成插值帧的方法,装置和计算机程序产品
    • US07899122B2
    • 2011-03-01
    • US11368440
    • 2006-03-07
    • Kazuyasu OhwakiGoh ItohNao Mishima
    • Kazuyasu OhwakiGoh ItohNao Mishima
    • H04N7/12
    • H04N7/014H04N19/132H04N19/553H04N19/573H04N19/587H04N19/61
    • A method for generating an interpolation frame between first and second reference frames includes dividing an interpolation frame into several interpolation areas; detecting a most correlated combination from several combinations between first reference areas and second reference areas for each interpolation area; obtaining a motion vector from the first and second reference areas; determining whether the first reference areas and the second reference areas are in a high-correlated area or a low-correlated area; giving the motion vector to the motion vector detected area, the motion vector detected area corresponding to the interpolation area which is determined to be the high-correlated area in the first and second reference areas; determining a motion vector to be given to the motion vector undetected area; and generating the interpolation frame based on the motion vector given to the motion vector detected area and the motion vector determined for the motion vector undetected area.
    • 一种用于在第一和第二参考帧之间产生插值帧的方法包括:将内插帧划分成若干内插区域; 从每个插值区域的第一参考区域和第二参考区域之间的多个组合中检测最相关的组合; 从所述第一和第二参考区域获得运动矢量; 确定第一参考区域和第二参考区域是否处于高相关区域或低相关区域中; 将所述运动矢量赋予所述运动矢量检测区域,所述运动矢量检测区域对应于被确定为所述第一和第二参考区域中的所述高相关区域的所述内插区域; 确定要给予所述运动矢量未检测区域的运动矢量; 并且基于给予运动矢量检测区域的运动矢量和为运动矢量未检测区域确定的运动矢量生成插值帧。
    • 8. 发明申请
    • IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD
    • 图像处理装置和图像处理方法
    • US20100232697A1
    • 2010-09-16
    • US12560838
    • 2009-09-16
    • Nao MishimaGoh Itoh
    • Nao MishimaGoh Itoh
    • G06K9/00
    • G06K9/4647G06K9/6212G06T5/002G06T5/20G06T5/40G06T2207/20012G06T2207/20192H04N19/61H04N19/86
    • An image processing apparatus includes a gradient calculator that calculates a direction and a magnitude of a gradient of each pixel in an input image using neighboring pixel values; a histogram calculator that calculates a Histogram of Oriented Gradients containing plural sampled directions from the directions and the magnitudes of the gradients calculated for the pixels in a region including the pixel being processed; a storing unit that stores plural smoothing filters and associated Histograms of Oriented Gradients; a search unit that calculates errors between Histogram of Oriented Gradients calculated for the pixel being processed and the Histograms of Oriented Gradients stored in the storing unit and searches the Histogram of Oriented Gradients that has the minimum error; and a filter processing unit that acquires one of the smoothing filters stored in association with the Histogram of Oriented Gradients having the minimum error and determines a corrected pixel value of the pixel being processed by filter processing with the acquired smoothing filter.
    • 一种图像处理装置,包括:梯度计算器,使用相邻像素值计算输入图像中每个像素的梯度的方向和幅度; 直方图计算器,其从包括正在处理的像素的区域中的像素计算的方向和梯度的大小计算包含多个取样方向的定向梯度的直方图; 存储单元,其存储多个平滑滤波器和相关联的定向梯度的直方图; 搜索单元,其计算针对正被处理的像素计算的定向梯度的直方图和存储在存储单元中的定向梯度的直方图之间的误差,并搜索具有最小误差的定向梯度的直方图; 以及滤波处理单元,其获取与具有最小误差的定向梯度的直方图相关联地存储的平滑滤波器之一,并且通过所获取的平滑滤波器确定通过滤波处理处理的像素的校正像素值。
    • 10. 发明授权
    • Frame interpolation and apparatus using frame interpolation
    • 帧插值和使用帧插值的装置
    • US07098959B2
    • 2006-08-29
    • US10657174
    • 2003-09-09
    • Nao MishimaGoh Itoh
    • Nao MishimaGoh Itoh
    • H04N7/01
    • H04N7/0132H04N5/145H04N7/0112H04N7/014
    • A first motion vector is estimated by using a first frame and a second frame that follows the first frame. A support frame is generated from at least either the first or the second frame by using the first motion vector. The support frame is divided into a plurality of small blocks. Motion vector candidates are estimated by using the first and second frames, in relation to each of the small blocks. A small block on the first frame, a small block on the second frame and the small blocks on the support frame are examined. The small block on the first frame and the small block on the second frame correspond to each of the motion vector candidates. A second motion vector is selected from the motion vector candidates, and points the small block on the first frame and the small block on the second frame which have the highest correlation with each of the small blocks on the support frame. An interpolated frame is generated from at least either the first or the second frame by using the second motion vector.
    • 通过使用跟随第一帧的第一帧和第二帧来估计第一运动矢量。 通过使用第一运动矢量从至少第一帧或第二帧产生支持帧。 支撑框架被分成多个小块。 通过使用相对于每个小块的第一和第二帧来估计运动矢量候选。 检查第一帧上的小块,第二帧上的小块和支持帧上的小块。 第一帧上的小块和第二帧上的小块对应于每个运动矢量候选。 从运动矢量候选中选择第二运动矢量,并将第一帧上的小块和与支撑帧上的每个小块具有最高相关性的第二帧上的小块指向。 通过使用第二运动矢量从至少第一帧或第二帧产生内插帧。