公开(公告)号：US07957557B2

公开(公告)日：2011-06-07

申请号：US11792084

申请日：2005-12-09

申请人： Nobuyuki Otsu ,  Masaaki Kawai

发明人： Nobuyuki Otsu ,  Masaaki Kawai

IPC分类号： G06K9/00 ,  H04W4/00

CPC分类号： G06K9/32 ,  G06K2009/3291 ,  G06T7/20

摘要： A tracing device and a tracing method for realizing a real-time trace of a moving object such as a person from a time-varying image by method of a light processing load, and for learning features through the trace thereby to realize a trace of higher precision. The tracing device divides time-varying data inputted into partial images (in a strip or rectangle shape), and compares the background image containing no tracing object thereby with the current image thereby to extract the divided image having the tracing object. In order to discriminate the tracing object, moreover, the tracing device calculates the color high-level local self-correlated data, from which the features of color and shape can be extracted all at once, and performs the discrimination on the basis of a distance from the featuring data of the tracing object registered. The tracing device updates the background image and the registered featuring data into the latest ones. The features are acquired while tracing the tracing object, and the object is discriminated by utilizing the features so that a strong and highly precise trace can be realized.

摘要翻译： 一种跟踪装置和跟踪方法，用于通过光处理负载的方法实现来自时变图像的人的移动物体的实时轨迹，并且通过轨迹学习特征，从而实现更高的轨迹 精确。 跟踪装置将输入的部分图像（条形或矩形）中的时变数据分割，并将不含跟踪对象的背景图像与当前图像进行比较，从而提取具有跟踪对象的分割图像。 此外，为了区分跟踪对象，跟踪装置计算出可以一次性提取颜色和形状的特征的颜色高级局部自相关数据，并且基于距离进行鉴别 从跟踪对象的特征数据注册。 跟踪设备将背景图像和已注册的特征数据更新为最新的。 在跟踪跟踪对象时获取特征，并且通过利用特征来区分对象，从而可以实现强烈和高精度的跟踪。

公开(公告)号：US20080187172A1

公开(公告)日：2008-08-07

申请号：US11792084

申请日：2005-12-09

申请人： Nobuyuki Otsu ,  Masaaki Kawai

发明人： Nobuyuki Otsu ,  Masaaki Kawai

IPC分类号： G06K9/00

CPC分类号： G06K9/32 ,  G06K2009/3291 ,  G06T7/20

摘要： A tracing device and a tracing method for realizing a real-time trace of a moving object such as a person from a time-varying image by method of a light processing load, and for learning features through the trace thereby to realize a trace of higher precision. The tracing device divides time-varying data inputted into partial images (in a strip or rectangle shape), and compares the background image containing no tracing object thereby with the current image thereby to extract the divided image having the tracing object. In order to discriminate the tracing object, moreover, the tracing device calculates the color high-level local self-correlated data, from which the features of color and shape can be extracted all at once, and performs the discrimination on the basis of a distance from the featuring data of the tracing object registered. The tracing device updates the background image and the registered featuring data into the latest ones. The features are acquired while tracing the tracing object, and the object is discriminated by utilizing the features so that a strong and highly precise trace can be realized.

摘要翻译： 一种跟踪装置和跟踪方法，用于通过光处理负载的方法实现来自时变图像的人的移动物体的实时轨迹，并且通过轨迹学习特征，从而实现更高的轨迹 精确。 跟踪装置将输入的部分图像（条形或矩形）中的时变数据分割，并将不含跟踪对象的背景图像与当前图像进行比较，从而提取具有跟踪对象的分割图像。 此外，为了区分跟踪对象，跟踪装置计算出可以一次性提取颜色和形状的特征的颜色高级局部自相关数据，并且基于距离进行鉴别 从跟踪对象的特征数据注册。 跟踪设备将背景图像和已注册的特征数据更新为最新的。 在跟踪跟踪对象时获取特征，并且通过利用特征来区分对象，从而可以实现强烈和高精度的跟踪。

公开(公告)号：US08423485B2

公开(公告)日：2013-04-16

申请号：US12733561

申请日：2008-09-12

申请人： Tatsuya Harada ,  Hideki Nakayama ,  Rie Matsumoto ,  Yasuo Kuniyoshi ,  Nobuyuki Otsu

发明人： Tatsuya Harada ,  Hideki Nakayama ,  Rie Matsumoto ,  Yasuo Kuniyoshi ,  Nobuyuki Otsu

IPC分类号： G06F15/18

CPC分类号： G06F17/30265 ,  G06F17/3069 ,  G06F17/30722 ,  G06K9/00664 ,  G06K9/4609 ,  G06K9/6232

摘要： An image data processing system has a learning storage apparatus that stores projection matrixes obtained by canonical correlation analysis so as to derive, based on at least one of an image feature and a word feature, a latent variable as an abstract concept used for associating an image with a word corresponding thereto and that further stores information required for obtaining the latent variable acquired by use of the projection matrixes, a probability of occurrence of an arbitrary image feature from a certain latent variable and a probability of occurrence of an arbitrary word feature from a certain latent variable. In this way, a probability of the image feature and word feature being simultaneously outputted can be easily and quickly determined, thereby executing a high-speed annotation or retrieval with high precision.

摘要翻译： 图像数据处理系统具有学习存储装置，其存储通过规范相关分析获得的投影矩阵，以便基于图像特征和词特征中的至少一个导出潜变量作为用于关联图像的抽象概念 并且进一步存储获得通过使用投影矩阵获得的潜在变量所需的信息，从某个潜在变量发生任意图像特征的概率和来自一个特定潜在变量的任意单词特征的发生概率 某些潜在变量。 以这种方式，可以容易且快速地确定图像特征和单词特征同时输出的概率，从而以高精度执行高速注释或检索。

公开(公告)号：US4538227A

公开(公告)日：1985-08-27

申请号：US431384

申请日：1982-09-30

申请人： Kazuo Toraichi ,  Nobuyuki Otsu ,  Motomu Suzuki

发明人： Kazuo Toraichi ,  Nobuyuki Otsu ,  Motomu Suzuki

IPC分类号： A61B6/03 ,  A61B6/00 ,  G01B7/28 ,  G01B21/20 ,  G01N23/04 ,  G06T1/00 ,  G06T5/40 ,  G06T7/60 ,  G06T11/00 ,  G06F15/42

CPC分类号： G06T5/40 ,  G06T5/009 ,  G06T2207/10116 ,  G06T2207/30004

摘要： An image processor which can accurately and promptly obtain information about a ventricle of a living body, such as the boundary diagram, the volume, the centroid movement view and a three-dimensional view. An X-ray projection of a part to be diagnosed is quantized. The boundary and centroid of the part are obtained from the optimal ternary data using the variance of the gray-level of the image and the separation degree of a histogram. The volume and three-dimensional view of the part are obtained from this data using the gray-level method.

摘要翻译： 能够准确且及时地获取关于生物体的心室的信息的图像处理装置，例如边界图，体积，重心移动视图和三维视图。 量化被诊断部位的X射线投射。 使用图像的灰度方差和直方图的分离度，从最佳三元数据中获得该部分的边界和质心。 使用灰度方法从该数据中获得部分的体积和三维视图。

公开(公告)号：US5619589A

公开(公告)日：1997-04-08

申请号：US353323

申请日：1994-12-05

申请人： Nobuyuki Otsu ,  Takio Kurita ,  Shigesumi Kuwashima

发明人： Nobuyuki Otsu ,  Takio Kurita ,  Shigesumi Kuwashima

IPC分类号： G06K9/52 ,  G06K9/62 ,  G06K9/66

CPC分类号： G06K9/6217 ,  G06K9/52

摘要： An adaptive learning type general purpose image measurement and recognition method includes the steps of extracting a large number of basic initial features having values which are invariant to parallel displacement of an object to be caught in an image frame and which have additivity with respect to the image frame and performing statistical feature extraction having a learning function on the basis of a multivariate analysis method applied to the extracted initial features to thereby adaptively enable use for various types of measurement.

摘要翻译： 自适应学习型通用图像测量和识别方法包括以下步骤：提取大量基本初始特征，该基本初始特征具有对待被捕获的对象的平行位移不变的值，并且具有相对于图像具有相加性的值 并且基于应用于所提取的初始特征的多元分析方法来执行具有学习功能的统计特征提取，从而自适应地使得能够使用各种类型的测量。

公开(公告)号：US5427441A

公开(公告)日：1995-06-27

申请号：US116769

申请日：1993-09-07

申请人： Nobuyuki Otsu

发明人： Nobuyuki Otsu

IPC分类号： B60T8/1763 ,  B60T8/66 ,  B60T8/72

CPC分类号： B60T8/17636 ,  Y10S303/04

摘要： In an antilock brake control system, a predetermined ratio of a pressure reduction threshold value to a pseudo vehicular body speed is varied in accordance with predetermined sections of a range of the pseudo vehicular body speed.

摘要翻译： 在防抱死制动控制系统中，根据伪车辆车身速度的范围的预定部分，改变减压阈值与伪车身速度的预定比例。

公开(公告)号：US07957560B2

公开(公告)日：2011-06-07

申请号：US11808827

申请日：2007-06-13

申请人： Nobuyuki Otsu ,  Takuya Nanri

发明人： Nobuyuki Otsu ,  Takuya Nanri

IPC分类号： G06K9/00

CPC分类号： G06K9/00771 ,  G06K9/00335 ,  G06T7/254

摘要： An abnormal action detector is provided for accurately detecting the position of an object together with an abnormal action using a cubic higher-order local auto-correlation feature. The abnormal action detector comprises a computer which generates inter-frame differential data from moving image data, extracts cubic higher-order local auto-correlation feature data on a pixel-by-pixel basis, adds the feature data for pixels within a predetermined range including each of pixels, calculates an index indicative of abnormality of the added feature data with respect to a subspace indicative of a normal action, determines an abnormality when the index is larger than a predetermined value, and outputs the position of a pixel at which the abnormality is determined. The computer further finds a subspace which exhibits a normal action from past feature data in accordance with a principal component analysis approach. The abnormal action detector is capable of determining abnormality on a pixel-by-pixel basis and correctly detecting the position of an object which has shown an abnormal action.

摘要翻译： 提供了一种异常动作检测器，用于使用立方高阶局部自相关特征来精确地检测物体的位置和异常动作。 异常动作检测器包括从运动图像数据生成帧间差分数据的计算机，逐像素地提取立方高阶局部自相关特征数据，将像素的特征数据相加在预定范围内，包括 每个像素计算指示相对于指示正常动作的子空间的附加特征数据的异常的指标，当指标大于预定值时确定异常，并且输出异常的像素的位置 决心，决意，决定。 计算机还根据主成分分析方法找到表现出来自过去特征数据的正常动作的子空间。 异常动作检测器能够基于逐像素地确定异常，并且能够正确地检测出显示异常动作的对象的位置。

公开(公告)号：US20100021067A1

公开(公告)日：2010-01-28

申请号：US12304552

申请日：2007-06-13

申请人： Nobuyuki Otsu ,  Takuya Nanri

发明人： Nobuyuki Otsu ,  Takuya Nanri

IPC分类号： G06K9/46

CPC分类号： G06T7/001 ,  G06K9/522 ,  G06K9/6247 ,  G06T2207/30141

摘要： An abnormal area detecting apparatus is provided for detecting the presence or absence and the position of abnormality with high accuracy using higher-order local auto-correlation feature. The abnormal area detecting apparatus comprises means for extracting feature data from image data on a pixel-by-pixel basis through higher-order local auto-correlation; means for adding the feature data extracted by the feature data extracting means for pixels within a predetermined range including each of pixels spaced apart by a predetermined distance; means for calculating an index indicative of abnormality of feature data with respect to a subspace indicative of a normal area; means for determining an abnormality based on the index; and means for outputting a pixel position at which an abnormal is determined. The apparatus may extract a plurality of higher-order local auto-correlation feature data which differ in displacement width. Further, the apparatus may comprise means for finding a subspace indicative of a normal area based on a principal component vector from feature data in accordance with a principal component analysis approach. The apparatus is capable of determine an abnormality on a pixel-by-pixel basis, and capable of correctly detecting the position of an abnormal area.

摘要翻译： 提供了一种异常区域检测装置，用于使用高阶局部自相关特征以高精度检测异常的存在或不存在和位置。 异常区域检测装置包括：通过高阶局部自相关逐像素地从图像数据中提取特征数据的装置; 用于将由所述特征数据提取装置提取的特征数据相加的装置，用于将预定范围内的像素间隔开预定距离; 用于计算指示特征数据相对于指示正常区域的子空间异常的指标的装置; 用于根据该指标确定异常的装置; 以及用于输出确定异常的像素位置的装置。 该装置可以提取位移宽度不同的多个高阶局部自相关特征数据。 此外，该装置可以包括用于根据主成分分析方法基于来自特征数据的主成分向量来找出指示正常区域的子空间的装置。 该装置能够逐像素地确定异常，能够正确地检测异常区域的位置。

公开(公告)号：US5442716A

公开(公告)日：1995-08-15

申请号：US80976

申请日：1993-06-24

申请人： Nobuyuki Otsu ,  Takio Kurita ,  Shigesumi Kuwashima

发明人： Nobuyuki Otsu ,  Takio Kurita ,  Shigesumi Kuwashima

IPC分类号： G06K9/52 ,  G06K9/62 ,  G06K9/46

CPC分类号： G06K9/6217 ,  G06K9/52

摘要： An adaptive learning type general purpose image measurement and recognition method includes the steps of extracting a large number of basic initial features having values which are invariant to parallel displacement of an object to be caught in an image frame and which have additivity with respect to the image frame, and performing statistical feature extraction having a learning function on the basis of a multivariate analysis method applied to the extracted initial features to thereby adaptively enable use for various types of measurement. Further, An adaptive learning type general purpose image measurement and recognition apparatus includes a pick-up device for picking up objects of measurement in two dimensions, an image cutting-out device for partially cutting out video signals of the picked-up images, a correlating device for computing Nth order autocorrelation of the cut-out data, a memory device for storing coefficients of the autocorrelation, and an arithmetic controlling device respetive devices and for carrying out multivariate analysis based on the computed values to thereby adaptively enable use for various types of measurement.

摘要翻译： 自适应学习型通用图像测量和识别方法包括以下步骤：提取大量基本初始特征，该基本初始特征具有对待被捕获的对象的平行位移不变的值，并且具有相对于图像具有相加性的值 并且基于应用于所提取的初始特征的多元分析方法来执行具有学习功能的统计特征提取，从而自适应地使得能够用于各种类型的测量。 此外，自适应学习型通用图像测量和识别装置包括用于拾取二维测量对象的拾取装置，用于部分地截取拍摄图像的视频信号的图像切出装置，相关的 用于计算所述切出数据的第N阶自相关的装置，用于存储所述自相关系数的存储装置，以及运算控制装置再生装置，并且用于基于所计算的值执行多变量分析，从而自适应地使能各种类型 测量。

公开(公告)号：US09031294B2

公开(公告)日：2015-05-12

申请号：US13807135

申请日：2011-07-22

申请人： Hirokazu Nosato ,  Hidenori Sakanashi ,  Masahiro Murakawa ,  Takumi Kobayashi ,  Tetsuya Higuchi ,  Nobuyuki Otsu

发明人： Hirokazu Nosato ,  Hidenori Sakanashi ,  Masahiro Murakawa ,  Takumi Kobayashi ,  Tetsuya Higuchi ,  Nobuyuki Otsu

IPC分类号： G06K9/00 ,  G06K9/46 ,  G06T7/00

CPC分类号： G06K9/4671 ,  G06K9/0014 ,  G06K9/56 ,  G06K9/6247 ,  G06K2009/4666 ,  G06T7/0012 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10024 ,  G06T2207/30024

摘要： A region segmented image data creating system for histopathological images is provided. The region segmented image data creating system is capable of creating region segmented image data required to generating a region segmented image. A first bi-level image data creating section 12 creates first bi-level image data, in which nucleus regions can be discriminated from other regions, from histopathological image data. A second bi-level image data creating section 14 creates second bi-level image data, in which a background regions can be discriminated from other regions, from the histopathological image data. A three-level image data creating section 15 clarifies cytoplasm regions by computing a negative logical addition of the first bi-level image data and the second bi-level image data, and to create three-level image data as the region segmented image data.

摘要翻译： 提供了用于组织病理学图像的区域分割图像数据创建系统。 区域分割图像数据创建系统能够创建产生区域分割图像所需的区域分割图像数据。 第一双级图像数据创建部分12从组织病理学图像数据创建其中核区域可以与其他区域区分开的第一双层图像数据。 第二双级图像数据创建部分14从组织病理学图像数据创建其中背景区域可以与其他区域区分开的第二双层图像数据。 三级图像数据创建部分15通过计算第一双电平图像数据和第二双电平图像数据的负逻辑加法来澄清细胞质区域，并且创建三电平图像数据作为区域分割图像数据。