利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

9 条记录 (耗时 0.022 秒)

    Pattern recognition system
    3.
    发明授权
    Pattern recognition system 失效
    模式识别系统

    公开(公告)号：US5911002A

    公开(公告)日：1999-06-08

    申请号：US715592

    申请日：1996-09-18

    申请人： Satoshi Mitsuyama ,  Jun Motoike ,  Norio Oowada ,  Yasuaki Kojima

    发明人： Satoshi Mitsuyama ,  Jun Motoike ,  Norio Oowada ,  Yasuaki Kojima

    IPC分类号： G01N15/02 ,  G01N15/14 ,  G01N33/493 ,  G06F15/18 ,  G06K9/66 ,  G06N3/00 ,  G06T7/00 ,  G06K9/62 ,  G06E1/00

    CPC分类号： G06K9/6217 ,  G01N33/493 ,  G06K9/00147 ,  G06K9/6262 ,  G01N15/1463 ,  G01N2015/1488

    摘要： In a pattern recognition system provided with a pattern recognition processing unit having a network structure constructed of an input layer for inputting a feature parameter of a subject under recognition as input information an intermediate layer for processing the input information and an output layer for outputting a processed result output values of respective output nodes for constituting the output layer, corresponding to the input information, are compared with each other by the pattern recognition processing unit, and a classification item corresponding to the output node whose output value is maximum is stored into a storage unit as a recognized result with respect to the input information. The pattern recognition system is also provided with a reliability evaluating unit for setting a threshold with respect to an output value of each of the output nodes and for evaluating reliability of the recognized result based upon the output values of the respective output nodes. When the reliability evaluating unit judges that the reliability is high, the recognized result is stored into the storage unit.

    摘要翻译： 在具有图案识别处理单元的图案识别系统中，该图案识别处理单元具有由输入层构成的网络结构，该输入层用于输入被识别的被摄体的特征参数作为输入信息，用于处理输入信息的中间层和用于输出处理的输出层 对应于输入信息的用于构成输出层的各个输出节点的结果输出值通过模式识别处理单元相互比较，并且与输出值最大的输出节点对应的分类项目被存储到存储器 单位作为输入信息的公认结果。 模式识别系统还设置有可靠性评估单元，用于相对于每个输出节点的输出值设置阈值，并且用于基于各个输出节点的输出值来评估识别结果的可靠性。 当可靠性评估单元判断可靠性高时，将识别结果存储在存储单元中。

    Region segmentation method for particle images and apparatus thereof
    4.
    发明授权
    Region segmentation method for particle images and apparatus thereof 失效
    用于粒子图像的区域分割方法及其装置

    公开(公告)号：US5768412A

    公开(公告)日：1998-06-16

    申请号：US523523

    申请日：1995-09-01

    申请人： Satoshi Mitsuyama ,  Jun Motoike ,  Akihide Hashizume

    发明人： Satoshi Mitsuyama ,  Jun Motoike ,  Akihide Hashizume

    IPC分类号： G06K9/00 ,  G06T5/00 ,  G06K9/34

    CPC分类号： G06T7/0081 ,  G06K9/00127 ,  G06T7/0012 ,  G06T2207/10056 ,  G06T2207/20056 ,  G06T2207/30024

    摘要： In a region segmentation method for particle images, which photographs stained and non-stained object particles supplied through an image input optical system and which uses at least two of the red-colored image, green-colored image and blue-colored image to discriminate between a background region and an object region where the object particles exist, the region segmentation method includes the processes of: a first process of setting a first group of thresholds in density value for a first group of at least two images selected from the red-colored image, green-colored image and blue-colored image to extract regions greatly differing in density from the background region, and producing a first binary image from the first group of images; a second process of calculating for each pixel a quantity representing the magnitude of change of density in an area neighboring each of the pixels making up each of one or more second group images selected from the red-colored image, green-colored image and blue-colored image, comparing a change of density in the background region with the quantity representing the magnitude of change of density calculated for each pixel, setting a second group of thresholds for extracting regions whose cane of density is larger than tat of the background region, and producing a second binary image from the second group of images; and a third process of performing a logic operation on the first binary image and the second binary image to produce a third binary image showing the background region and the object region.

    摘要翻译： 在用于粒子图像的区域分割方法中，通过图像输入光学系统提供的照片染色和未染色的物体粒子，并且使用至少两个红色图像，绿色图像和蓝色图像来区分 背景区域和存在物体粒子的对象区域，区域分割方法包括以下处理：对于从红色中选择的至少两个图像的第一组，设置密度值的第一组阈值的第一处理 图像，绿色图像和蓝色图像以提取与背景区域密度大不相同的区域，以及从第一组图像产生第一二进制图像; 对于每个像素计算表示构成从红色图像，绿色图像和蓝色图像中选择的一个或多个第二组图像中的每一个的每个像素附近的区域中的浓度变化幅度的量的第二过程， 将背景区域中的浓度变化与表示为每个像素计算的浓度变化幅度的量进行比较，设定第二组阈值，以提取密度较大的背景区域的tat的区域，以及 从第二组图像产生第二二进制图像; 以及对所述第一二进制图像和所述第二二进制图像执行逻辑运算以产生示出所述背景区域和所述对象区域的第三二进制图像的第三处理。

    Pattern recognition apparatus and pattern recognition method
    5.
    发明授权
    Pattern recognition apparatus and pattern recognition method 有权
    模式识别装置和模式识别方法

    公开(公告)号：US06549661B1

    公开(公告)日：2003-04-15

    申请号：US09331150

    申请日：1999-06-17

    申请人： Satoshi Mitsuyama ,  Jun Motoike ,  Hitoshi Matsuo ,  Yasuaki Kojima

    发明人： Satoshi Mitsuyama ,  Jun Motoike ,  Hitoshi Matsuo ,  Yasuaki Kojima

    IPC分类号： G06K962

    CPC分类号： G06K9/00127 ,  G06K9/6217 ,  G06K9/6263

    摘要： Recognizable data storage apparatus stores an image feature parameter of an object and its classification result for those objects for which said classification results are evaluated as having high reliability and recognizable and for which a classification result is outputted by first pattern recognition apparatus, and recognition suspension data storage apparatus stores an image feature parameter for those objects for which said classification results are evaluated as having low reliability and as being suspended from recognition. Pattern recognition method constitution apparatus constructs second pattern recognition apparatus on the basis of the classification result stored in the recognizable data storage apparatus, and re-classification is conducted for those objects recognition of which is to be suspended. A neural network, for example, is used for the second pattern recognition apparatus. Wrong classification of objects due to an individual difference can be reduced and automated pattern recognition having high accuracy without depending on an individual difference can be accomplished.

    摘要翻译： 可识别数据存储装置存储被评价为具有高可靠性和可识别性的那些对象的对象的图像特征参数及其分类结果，并且由第一模式识别装置输出分类结果，并且识别暂停数据 存储装置存储所述分类结果被评估为具有低可靠性并被停止识别的那些对象的图像特征参数。 模式识别方法构成装置根据存储在可识别数据存储装置中的分类结果，构建第二模式识别装置，对于要暂停的对象识别进行重新分类。 例如，神经网络被用于第二模式识别装置。 可以减少由于个体差异导致的对象的错误分类，并且可以实现具有高精度的自动模式识别，而不依赖于个体差异。

    Method and apparatus for classifying white blood cells
    6.
    发明授权
    Method and apparatus for classifying white blood cells 失效
    白细胞分类方法及装置

    公开(公告)号：US4850024A

    公开(公告)日：1989-07-18

    申请号：US720013

    申请日：1985-04-04

    申请人： Jun Motoike ,  Akihide Hashizume ,  Ryuichi Suzuki

    发明人： Jun Motoike ,  Akihide Hashizume ,  Ryuichi Suzuki

    IPC分类号： G01N33/48 ,  G01N15/14 ,  G01N33/49 ,  G06K9/00 ,  G06Q50/22 ,  G06Q50/24 ,  G06T1/00

    CPC分类号： G06K9/00127 ,  G01N15/1468 ,  G01N15/1475

    摘要： An apparatus for classifying leukocytes comprises a sample image preprocessing unit which modifies the pattern of the nucleus of each of predetermined number of leukocytes extracted from the image of a blood sample, a unit for analyzing each of the processed nucleus patterns and broadly classifying each of the leukocytes into a typical or quasi-typical band form neutrophil, a typical or quasi-typical segmented neutrophil, or other neutrophil in an intermixture domain or a leukocyte other than a neutrophil, and a unit for calculating sample estimation indexes from the numbers of typical and quasi-typical neutrophils and the total number of neutrophils, classifying each of the neutrophils in the intermixture domain into a band form or a segmented neutrophil in accordance with the estimation indexes, and adding the numbers of intermixed band form and segmented neutrophils to the numbers of typical or quasi-typical band form and segmented neutrophils, respectively.

    摘要翻译： 用于分类白细胞的装置包括样本图像预处理单元，其对从血液样本的图像提取的预定数量的白细胞中的每一个白细胞的核的图案进行修改，分析每个经处理的核图案的单元，并且对 白细胞成为典型或准典型的带状中性粒细胞，典型或准典型的分段嗜中性粒细胞，或混合结构域中的其他嗜中性粒细胞或嗜中性粒细胞以外的白细胞，以及用于从典型和准 准典型嗜中性粒细胞和嗜中性粒细胞总数，根据估计指标将混合结构域中的每个嗜中性粒细胞分类为带状或分段嗜中性粒细胞，并将混合带形式和分段嗜中性粒细胞数加到 典型或准典型的带状和分段嗜中性粒细胞。

    Visual information processing apparatus
    8.
    发明授权
    Visual information processing apparatus 失效
    视觉信息处理装置

    公开(公告)号：US4346405A

    公开(公告)日：1982-08-24

    申请号：US195859

    申请日：1980-10-10

    申请人： Haruo Yoda ,  Jun Motoike

    发明人： Haruo Yoda ,  Jun Motoike

    IPC分类号： H04N7/18 ,  B66B1/34 ,  G06T7/20 ,  G09G5/36

    CPC分类号： B66B1/3476 ,  G06T7/2013 ,  G06T2207/10016

    摘要： A visual information processing apparatus which processes image data produced by a TV camera to detect the change in image with the lapse of time. The visual information processing apparatus comprises a circuit which generates the data of coordinates X and Y that represent a scanning position on the image, a memory for storing a plurality of microprograms, a control circuit which addresses an initial instruction of a microprogram corresponding to the coordinate Y when the coordinate X reached a particular value that is specified by an external unit, and a unit for processing the image data from said TV camera in accordance with a microprogram that is read out from said memory, wherein the same microprograms are periodically read out by bringing least significant several bits among the binary data which represents the coordinate Y to correspond to an initial address of each of the microprograms. With this visual information processing apparatus, the TV screen is divided into a plurality of blocks and a reduced number of microprograms are required for processing the image data.

    摘要翻译： 一种视觉信息处理装置，其处理由电视摄像机产生的图像数据，以随着时间的流逝检测图像的变化。 视觉信息处理装置包括生成表示图像上的扫描位置的坐标X和Y的数据的电路，存储多个微程序的存储器，对应于该坐标的微程序的初始指令的控制电路 当坐标X达到由外部单元指定的特定值时的Y，以及用于根据从所述存储器读出的微程序处理来自所述TV摄像机的图像数据的单元，其中周期性地读出相同的微程序 通过在表示坐标Y的二进制数据中带来最低有效数位来对应于每个微程序的初始地址。 利用该视觉信息处理装置，电视屏幕被分成多个块，并且需要减少数量的微程序来处理图像数据。

    Image data processor
    9.
    发明授权
    Image data processor 失效
    图像数据处理器

    公开(公告)号：US4254400A

    公开(公告)日：1981-03-03

    申请号：US98074

    申请日：1979-11-28

    申请人： Haruo Yoda ,  Jun Motoike

    发明人： Haruo Yoda ,  Jun Motoike

    IPC分类号： H04N7/18 ,  B66B1/34 ,  G06K9/46 ,  G06T7/20 ,  G08B13/194 ,  G06K9/50

    CPC分类号： B66B1/3476 ,  G06K9/46 ,  G08B13/19602 ,  G08B13/19634 ,  G08B13/19676

    摘要： An image data processor for recognizing the degree of variation in the object in the image by dividing an image plane into a plurality of block regions and by sequentially comparing an input image and a background image for each of the divided block regions. The data to be used for comparing the input image and the background image are either the number of occurences of preset amplitude relationships of the signals which are produced by extracting the signals of plural pairs of picture elements in spacially preset relative position relationships from the output signals of an image pickup device while sequentially shifting the positions of the picture elements and by accomplishing the counting operations for each pair of the picture elements when the picture element extracted is included in a preset block region or the data which are produced by linearly transforming the data of the number of occurences.

    摘要翻译： 一种图像数据处理器，用于通过将图像平面划分成多个块区域并且通过对每个分割块区域的输入图像和背景图像进行顺序比较来识别图像中的对象的变化程度。 用于比较输入图像和背景图像的数据是通过从输出信号提取空间预设的相对位置关系中的多对图像元素的信号而产生的信号的预设幅度关系的发生次数 的图像拾取装置，同时顺序地移动图像元素的位置，并且当提取的图像元素被包括在预设块区域中时，并且通过对每对图像元素执行计数操作，或者通过线性变换数据产生的数据 的发生次数。