公开(公告)号：US20120020528A1

公开(公告)日：2012-01-26

申请号：US13177809

申请日：2011-07-07

申请人： Hideshi YAMADA

发明人： Hideshi YAMADA

IPC分类号： G06K9/00

CPC分类号： G06T7/11 ,  G06T7/194 ,  G06T2207/10024 ,  G06T2207/20076 ,  G06T2207/20104

摘要： An image processing apparatus includes an obtaining unit obtaining an image including a closed curve input which encloses an object in an input image, a generation unit generating a distance image having pixel values of individual pixels corresponding to distances from the input closed curve in accordance with a shape of the curve, a calculation unit calculating an input-image energy of the input image including a distance energy changed based on the distances of the pixels or a likelihood energy changed based on likelihoods of the pixels based on color distribution models of an object region and a non-object region in the distance image and a color energy changed in accordance with color differences between adjacent pixels in the distance image, and a generation unit generating a mask image by minimizing the input-image energy and assigning an attribute representing the object region or an attribute representing the non-object region.

摘要翻译： 图像处理装置包括：获取单元，获得包含输入图像中的物体的闭合曲线输入的图像;生成单元，生成与根据输入的闭合曲线的距离对应的各个像素的像素值的距离图像 曲线形状，计算单元，其计算输入图像的输入图像能量，该输入图像包括基于像素的距离而改变的距离能量或基于基于像素的颜色分布模型的像素的可能性而改变的似然度能量 以及距离图像中的非对象区域和根据距离图像中的相邻像素之间的颜色差变化的颜色能量，以及通过使输入图像能量最小化并分配表示对象的属性来生成掩模图像的生成单元 区域或表示非对象区域的属性。

公开(公告)号：US20110050685A1

公开(公告)日：2011-03-03

申请号：US12859110

申请日：2010-08-18

申请人： Hideshi YAMADA

发明人： Hideshi YAMADA

IPC分类号： G06T15/00

CPC分类号： G06T15/10

摘要： An image processing apparatus, which creates a pseudo three-dimensional image that improves depth perception of the image, includes: an input image acquiring unit that acquires an input image and a binary mask image that specifies an object area on the input image; a combining unit that extracts pixels in an area inside a quadrangular frame picture of the input image and pixels in the object area, specified by the binary mask image, on the input image to create a combined image; and a frame picture combining position determining unit that determines a position on the combined image at which the quadrangular frame picture is placed so that one of a pair of opposite edges of the quadrangular frame picture includes an intersection with boundary of the object area and another of the pair does not include an intersection with the boundary of the object area.

摘要翻译： 一种创建改善图像深度感知的伪三维图像的图像处理装置，包括：输入图像获取单元，其获取输入图像的指定对象区域的输入图像和二值掩模图像; 合成单元，其在输入图像上提取输入图像的四边形帧图像内的区域中的像素和由二进制掩模图像指定的对象区域中的像素，以产生组合图像; 以及帧图像组合位置确定单元，其确定放置四边形帧图像的组合图像上的位置，使得四边形帧图像的一对相对边缘中的一个包括与对象区域的边界和另一个 该对不包括与对象区域的边界的交集。

公开(公告)号：US20120057783A1

公开(公告)日：2012-03-08

申请号：US13222891

申请日：2011-08-31

申请人： Hideshi YAMADA

发明人： Hideshi YAMADA

IPC分类号： G06K9/46

CPC分类号： G06T7/143 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/20021 ,  G06T2207/20076

摘要： An image processing apparatus includes a feature vector extraction unit that extracts feature vectors of sample pixels, for each local region including the sample pixels, in an input image; a weight calculation unit that calculates weights for the local regions on the basis of the positional relationship with the local regions, for divided regions that divide the input image; a feature distribution model calculation unit that calculates an average with weights as a feature distribution model in a local region obtained by adding the weights calculated from the local regions to the feature vectors of the local regions, for each of the divided regions; and a pixel likelihood calculation unit that calculates pixel likelihood for each pixel in the input image on the basis of the feature distribution model.

摘要翻译： 图像处理装置包括特征向量提取单元，其在输入图像中为每个包含样本像素的局部区域提取样本像素的特征向量; 权重计算单元，对于划分输入图像的分割区域，基于与局部区域的位置关系来计算局部区域的权重; 特征分布模型计算单元，对于每个分割区域，计算通过将从局部区域计算的权重与局部区域的特征向量相加而获得的局部区域中的权重作为特征分布模型的平均值; 以及像素似然度计算单元，其基于特征分布模型来计算输入图像中的每个像素的像素似然度。

公开(公告)号：US20110029469A1

公开(公告)日：2011-02-03

申请号：US12845968

申请日：2010-07-29

申请人： Hideshi YAMADA

发明人： Hideshi YAMADA

IPC分类号： G06F15/18 ,  G06F17/10

CPC分类号： G06F17/18 ,  G06K9/6221 ,  G06K9/6277

摘要： An information processing apparatus, which performs setting of a mixture model function representing a mixture model along with adaptively adjusting the number of model components mixed in the mixture model, includes an acquisition section configured to acquire a first data sample and a second data sample, both of which are composed of multi-dimensions; a mixture-model-function generation section configured to generate a mixture model function on the basis of the first data sample; a mixture-model-function goodness-of-fit calculation section configured to calculate a goodness of fit for the mixture model function on the basis of the second data sample; and a mixture-model-function update section configured to update the mixture model function so as to adjust the number of model components mixed in a mixture model, which are represented by the mixture model function, on the basis of the goodness of fit for the mixture model function.

摘要翻译： 一种信息处理装置，其执行表示混合模型的混合模型函数的设置，以及自适应地调整混合模型中混合的模型分量的数量，包括：获取部，被配置为获取第一数据样本和第二数据样本， 其中包括多维度; 混合模型函数生成部，被配置为基于第一数据样本生成混合模型函数; 配置为基于第二数据样本计算混合模型函数的拟合优度的混合模型函数拟合优度计算部分; 以及混合模型功能更新部，其被配置为基于所述混合模型函数的适合度来更新混合模型函数，以便调整由混合模型函数表示的混合模型中混合的模型分量的数量 混合模型功能。

公开(公告)号：US20100061628A1

公开(公告)日：2010-03-11

申请号：US12551612

申请日：2009-09-01

申请人： Hideshi YAMADA

发明人： Hideshi YAMADA

IPC分类号： G06K9/03 ,  G06K9/48

CPC分类号： G06T7/11 ,  G06T7/194 ,  G06T2207/10024

摘要： An image processing apparatus includes a defined binary image generating unit configured to generate a defined binary image associated with a level image, which is associated with an input image, the level image having pixel values of pixels represented using a first value, by regarding a pixel as a defined or undefined region pixel and setting the pixel to have a predetermined second or third value; and an estimated foreground color image generation unit configured to generate an estimated foreground color image associated with the input image, by setting the pixel values of the pixels regarded as the undefined region pixels in the defined binary image to pixel values of pixels in the input image corresponding to pixels for which distances each obtained from an integrated value of the amounts of change in continuity information are shortest from among the pixels that are regarded as the defined region pixels.

摘要翻译： 一种图像处理装置，包括定义的二进制图像生成单元，被配置为生成与输入图像相关联的与图像相关联的定义的二值图像，所述二值图像具有使用第一值表示的像素的像素值， 作为定义的或未定义的区域像素，并将像素设置为具有预定的第二或第三值; 以及估计的前景彩色图像生成单元，被配置为通过将所定义的二值图像中被认为是未定义区域像素的像素的像素值设置为输入图像中的像素的像素值来生成与输入图像相关联的估计前景彩色图像 对应于从被认为是所定义的区域像素的像素中，从连续性信息的变化量的积分值获得的距离最短的像素。

公开(公告)号：US20120304649A1

公开(公告)日：2012-12-06

申请号：US13485383

申请日：2012-05-31

申请人： Ryusuke MATSUYAMA ,  Masayoshi KOBAYASHI ,  Takeo ODA ,  Atsushi HORIKAWA ,  Shigeru HAYASHI ,  Kazuo SHIMODAIRA ,  Kazuaki MATSUURA ,  Hideshi YAMADA ,  Youji KUROSAWA ,  Hitoshi FUJIWARA

发明人： Ryusuke MATSUYAMA ,  Masayoshi KOBAYASHI ,  Takeo ODA ,  Atsushi HORIKAWA ,  Shigeru HAYASHI ,  Kazuo SHIMODAIRA ,  Kazuaki MATSUURA ,  Hideshi YAMADA ,  Youji KUROSAWA ,  Hitoshi FUJIWARA

IPC分类号： F02C7/22

CPC分类号： F23R3/14 ,  F23R3/286 ,  Y02T50/675

摘要： A fuel injector includes: a pilot injector configured to spray fuel so as to form a first combustion region in a combustion chamber; and a main injector provided coaxially with the pilot injector so as to surround the pilot injector and configured to supply a fuel-air mixture that is a mixture of the fuel and air to form a second combustion region in the combustion chamber, wherein the main injector includes: a first inflow channel through which the air having a major flow component in an axial direction is taken; a second inflow channel through which the air having a major flow component in a radial direction is taken and which causes the air therein to meet the air from the first inflow channel; and a main fuel injecting portion configured to inject the fuel only to the second inflow channel.

摘要翻译： 燃料喷射器包括：引燃喷射器，构造成喷射燃料以在燃烧室中形成第一燃烧区域; 以及主喷射器，其与所述先导喷射器同轴地设置成围绕所述引燃喷射器并且构造成供应作为所述燃料和空气的混合物的燃料 - 空气混合物以在所述燃烧室中形成第二燃烧区域，其中所述主喷射器 包括：沿轴向方向具有主要流动分量的空气通过该第一流入通道; 第二流入通道，​​其中沿着径向方向具有主要流动分量的空气通过该第二流入通道引起其中的空气与来自第一流入通道的空气相遇; 以及主燃料喷射部，其构造成仅将燃料喷射到第二流入流路。

公开(公告)号：US20120294583A1

公开(公告)日：2012-11-22

申请号：US13450962

申请日：2012-04-19

申请人： Junichi KOSAKA ,  Hideshi YAMADA

发明人： Junichi KOSAKA ,  Hideshi YAMADA

IPC分类号： H04N5/93

CPC分类号： G06T13/80 ,  G06T3/4038

摘要： An image processing apparatus including an input terminal that receives a plurality of image units that are temporally or spatially continuous; an image processing unit that performs image processing on the plurality of image units by iteratively performing the image processing on subsets of the plurality of image units; and a display image generating unit that controls a display to display the plurality of image units when the image processing unit begins performing the image processing; display, at a time of a completion of intermediate processing of a subset of the plurality of image units by the image processing unit, an intermediate processed image including the processed subset of the plurality of image data units; and display, after completion of the processing of the plurality of image units by the image processing unit, a complete processed image including the processed plurality of image data units.

摘要翻译： 一种图像处理装置，包括：输入端子，其接收时间上或空间上连续的多个图像单元; 图像处理单元，通过对所述多个图像单元的子集反复执行图像处理，对所述多个图像单元进行图像处理; 以及显示图像生成单元，其在图像处理单元开始进行图像处理时控制显示器显示多个图像单元; 在由所述图像处理单元完成所述多个图像单元的子集的中间处理时，显示包括所述多个图像数据单元的经处理子集的中间处理图像; 并且在由所述图像处理单元完成所述多个图像单元的处理完成之后，显示包括所处理的多个图像数据单元的完整处理图像。

公开(公告)号：US20110229022A1

公开(公告)日：2011-09-22

申请号：US13043960

申请日：2011-03-09

申请人： Hideshi YAMADA

发明人： Hideshi YAMADA

IPC分类号： G06K9/00

CPC分类号： G06T3/00 ,  H04N1/6086

摘要： An image processing apparatus includes a circumstance vector generation unit configured to acquire information indicating circumstances, to digitize the information, and to generate a circumstance vector, a conversion parameter calculation unit configured to weighted-add several conversion parameters specified by the circumstance vector among a plurality of previously prepared conversion parameters for image conversion, and a converted image generation unit configured to perform image conversion using the conversion parameters obtained by the weighted-adding with respect to an original image to be processed so as to generate a converted image.

摘要翻译： 一种图像处理装置，包括环境矢量生成单元，被配置为获取指示环境的信息，数字化信息，并生成环境矢量;变换参数计算单元，被配置为对由所述环境矢量指定的多个转换参数 以及转换图像生成单元，被配置为使用通过对要处理的原始图像进行加权相加获得的转换参数来执行图像转换，以便生成转换后的图像。