利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

10 条记录 (耗时 0.03 秒)

    Methods for determining the exterior points of an object in a background
    1.
    发明授权
    Methods for determining the exterior points of an object in a background 失效
    用于确定背景中物体的外部点的方法

    公开(公告)号：US5579409A

    公开(公告)日：1996-11-26

    申请号：US159641

    申请日：1993-11-30

    申请人： Akhileswar G. Vaidyanathan ,  Hooshmand M. Kalayeh

    发明人： Akhileswar G. Vaidyanathan ,  Hooshmand M. Kalayeh

    IPC分类号： G01B11/24 ,  G06K9/00 ,  G06K9/48 ,  G06T1/00 ,  G06T5/00 ,  G06T5/40 ,  G06T7/00 ,  G06T7/60 ,  G06T9/20 ,  G06T11/40 ,  G06K9/46

    CPC分类号： G06T7/0083 ,  G06K9/00127 ,  G06K9/48 ,  G06T11/40 ,  G06T7/0012 ,  G06T9/20 ,  G06T2207/10016 ,  G06T2207/10056 ,  G06T2207/20148 ,  G06T2207/30024

    摘要： Accessing the exterior points of an object is used in the area of object identification when it is important to use the information in the local exterior environment of an object in order to extract a feature which may be useful for object recognition. Examples of this type of feature which are important for recognizing and classifying objects occur in the area if bacterial detection. Adaptive classification is a way of making the analysis independent of variations in imaging conditions, such as lighting, positioning, electronic amplification, etc. Two general methods can be used to access the local exterior environment of an object, knowing the perimeter points of the object. In the first method, the shape of an annular exterior region around the object of interest can be made to follow the shape of the object itself. In the second method, an known exterior shape, such as a circle, is used to characterize the exterior contour region, approximating the shape of the object.

    摘要翻译： 在对象识别的区域中使用对象的外部点来访问对象的本地外部环境中的信息是重要的，以便提取可能对对象识别有用的特征。 如果细菌检测，这种对识别和分类对象重要的这种特征的实例发生在该区域中。 自适应分类是使得分析独立于诸如照明，定位，电子放大等的成像条件的变化的方式。可以使用两种一般方法来访问对象的局部外部环境，知道对象的周边点 。 在第一种方法中，可以使感兴趣物体周围的环形外部区域的形状遵循物体本身的形状。 在第二种方法中，使用已知的外部形状（例如圆形）来表征外部轮廓区域，近似对象的形状。

    Nonwoven sheet products made from plexifilamentary film fibril webs
    2.
    发明授权
    Nonwoven sheet products made from plexifilamentary film fibril webs 失效
    由丛状薄膜原纤维网制成的无纺布片材

    公开(公告)号：US06070635A

    公开(公告)日：2000-06-06

    申请号：US62349

    申请日：1998-04-17

    申请人： Ralph A. Franke ,  Hyun S. Lim ,  Michael P. Milone ,  R. Gail Raty ,  Akhileswar G. Vaidyanathan

    发明人： Ralph A. Franke ,  Hyun S. Lim ,  Michael P. Milone ,  R. Gail Raty ,  Akhileswar G. Vaidyanathan

    IPC分类号： D04H1/72 ,  D04H3/16 ,  G01B11/24 ,  G01R9/00

    CPC分类号： D04H3/16 ,  D04H1/724 ,  Y10S428/903 ,  Y10T428/24826 ,  Y10T428/24942 ,  Y10T428/24992 ,  Y10T428/249978 ,  Y10T442/608

    摘要： This invention relates to improved sheet products and specifically to improved nonwoven sheet products made from highly oriented plexifilamentary film-fibril webs. The improved sheet products have high opacity and strength with a much wider range of porosity or Gurley Hill Porosity Values. In particular, sheet products made in accordance with the present invention have considerably higher Gurley Hill Porosity Values than similar weight sheet products subject to the same finishing treatments in accordance with prior known sheet materials. Similarly, sheet products made in accordance with the present invention can be made which have much lower Gurley Hill Porosity Values than prior sheet materials. The invention includes numerous methods and data characterizing the webs and sheets that form the improved sheet materials.

    摘要翻译： 本发明涉及改进的片材产品，特别涉及由高取向的有丝纤维膜 - 原纤维网制成的改进的非织造片材产品。 改进的片材产品具有高的不透明度和强度，具有更宽的孔隙率或Gurley Hill孔隙度值。 特别地，根据本发明制成的片材产品具有相当高的古利山孔隙度值，而不是按照现有的已知片材进行相同的整理处理的类似重量片材产品。 类似地，可以制造根据本发明制成的片材产品，其具有比先前的片材材料低得多的古利山孔隙度值。 本发明包括形成改进的片材的幅材和片材的许多方法和数据。

    Parallel processing method and system for identifying valid objects in a background of an image
    5.
    发明授权
    Parallel processing method and system for identifying valid objects in a background of an image 失效
    用于识别图像背景中的有效对象的并行处理方法和系统

    公开(公告)号：US5608820A

    公开(公告)日：1997-03-04

    申请号：US283310

    申请日：1994-07-29

    申请人： Akhileswar G. Vaidyanathan

    发明人： Akhileswar G. Vaidyanathan

    IPC分类号： G01B11/24 ,  G01N15/00 ,  G06K9/48 ,  G06M11/00 ,  G06T5/00 ,  G06T5/40 ,  G06T7/00 ,  G06T7/60 ,  G06T9/20 ,  G06T11/40 ,  G06K9/00

    CPC分类号： G06T11/40 ,  G06K9/0014 ,  G06K9/48 ,  G06T7/0012 ,  G06T7/0081 ,  G06T9/20 ,  G06T2207/20148 ,  G06T2207/30024 ,  G06T2207/30128

    摘要： The present invention relates to a parallel processing image analysis method and system for identifying objects in a background by generating a description, which may be either a histogram or co-occurrence matrix, of the gray level space of the image by using an entropic kernel to recursively analyze the gray level space for candidate objects and validating the presence of valid objects by comparing the candidate object attribute values to a defined set of valid object attribute values contained in a driver. The method may be used in a wide variety of industrial inspection techniques, including colony counting and the identification of discrete features in carpets and of pigment elements embedded in a polymer.

    摘要翻译： 本发明涉及一种并行处理图像分析方法和系统，用于通过使用熵核向所述图像的灰度级空间生成描述（可以是直方图或同现矩阵）来识别背景中的对象 通过将候选对象属性值与驱动程序中包含的一组有效对象属性值进行比较，递归地分析候选对象的灰度空间并验证有效对象的存在。 该方法可用于各种各样的工业检验技术，包括菌落计数和识别地毯中的离散特征以及嵌入聚合物中的颜料元素。

    Adaptive vision system
    7.
    发明授权
    Adaptive vision system 失效
    自适应视觉系统

    公开(公告)号：US5481620A

    公开(公告)日：1996-01-02

    申请号：US767339

    申请日：1991-09-27

    申请人： Akhileswar G. Vaidyanathan

    发明人： Akhileswar G. Vaidyanathan

    IPC分类号： G01B11/24 ,  G01N15/00 ,  G06K9/48 ,  G06M11/00 ,  G06T5/00 ,  G06T5/40 ,  G06T7/00 ,  G06T7/60 ,  G06T9/20 ,  G06T11/40 ,  G06K9/30 ,  G06K9/20

    CPC分类号： G06T11/40 ,  G06K9/0014 ,  G06K9/48 ,  G06T7/0012 ,  G06T7/0081 ,  G06T9/20 ,  G06T2207/20148 ,  G06T2207/30024 ,  G06T2207/30128

    摘要： The present invention relates to image analysis methods and systems for identifying objects in a background by generating a description, which may be either a histogram or co-occurrence matrix, of the gray level space of the image by using an entropic kernel to recursively analyze the gray level space for candidate objects and validating the presence of valid objects by comparing the candidate object attribute values to a defined set of valid object attribute values contained in a driver. The present invention includes recursive, iterative and parallel processing methods. The methods may be used in a wide variety of industrial inspection techniques, including colony counting and the identification of discrete features in carpets and of pigment elements embedded in a polymer.

    摘要翻译： 本发明涉及图像分析方法和系统，用于通过使用熵核生成图像的灰度级空间的描述（其可以是直方图或同现矩阵）来递归地分析图像分析方法和用于识别背景中的对象的系统 通过将候选对象属性值与驱动器中包含的一组有效对象属性值进行比较来验证候选对象的灰度级空间并验证有效对象的存在。 本发明包括递归，迭代和并行处理方法。 这些方法可用于各种各样的工业检验技术，包括菌落计数和地毯中分散特征的识别以及嵌入聚合物中的颜料元素。

    Method of identifying and characterizing a valid object by color
    9.
    发明授权
    Method of identifying and characterizing a valid object by color 失效
    通过颜色识别和表征有效对象的方法

    公开(公告)号：US5375177A

    公开(公告)日：1994-12-20

    申请号：US999703

    申请日：1992-12-31

    申请人： Akhileswar G. Vaidyanathan ,  Dennis B. Fowler

    发明人： Akhileswar G. Vaidyanathan ,  Dennis B. Fowler

    IPC分类号： G01V8/10 ,  G06T1/00 ,  G06T5/40 ,  G06T7/00 ,  G06T7/40 ,  G06T11/00 ,  G09G5/06 ,  G06K9/20 ,  G06K9/46

    CPC分类号： G06T7/408 ,  G06T11/001 ,  G06T7/0002 ,  G06T7/0083 ,  G09G5/06 ,  G06T2207/10024 ,  G06T2207/20148

    摘要： The present invention relates to a method of identifying and characterizing, by color, at least one valid object having at least one predetermined attribute value in a background. The method generates a plurality of images of a candidate object and the background, where each image is one of three primary color images or a black-and-white image. The method searches the image for a candidate object using an automatically calculated threshold gray level and determines the interior points of the candidate object. The method further determines the gray level value of the interior points in the image and calculates a color parameter for the interior points. The method thus enables one to characterize the candidate object by the color parameter and validate the candidate object having the valid object predetermined attribute value.

    摘要翻译： 本发明涉及通过颜色识别和表征在背景中具有至少一个预定属性值的至少一个有效对象的方法。 该方法产生候选对象和背景的多个图像，其中每个图像是三个原色图像之一或黑白图像。 该方法使用自动计算的阈值灰度级来搜索候选对象的图像，并确定候选对象的内部点。 该方法进一步确定图像中内部点的灰度值，并计算内部点的颜色参数。 因此，该方法使得能够通过颜色参数来表征候选对象，并且验证具有有效对象预定属性值的候选对象。

    Method of analyzing the texture of a surface and a carpet characterized by the method
    10.
    发明授权
    Method of analyzing the texture of a surface and a carpet characterized by the method 失效
    用该方法分析表面和地毯纹理的方法

    公开(公告)号：US5325301A

    公开(公告)日：1994-06-28

    申请号：US860774

    申请日：1992-03-27

    申请人： Warren F. Knoff ,  Michael J. Merrill ,  Barry Rubin ,  Akhileswar G. Vaidyanathan ,  James E. Van Trump ,  Theresa A. Weston

    发明人： Warren F. Knoff ,  Michael J. Merrill ,  Barry Rubin ,  Akhileswar G. Vaidyanathan ,  James E. Van Trump ,  Theresa A. Weston

    IPC分类号： D01F6/60 ,  D02G1/12 ,  D02G3/44 ,  D02J13/00 ,  D05C17/02 ,  G01N33/36 ,  G06F15/20

    CPC分类号： G01N33/367 ,  D02G1/12 ,  D02G3/445 ,  D02J13/001 ,  Y10T428/23936

    摘要： The present invention relates broadly to a method of image analysis for analyzing the texture of a surface, and to a saxony-type carpet having a tightly tailored surface texture characterized by this method. The method employs a model based on a second order co-occurrence matrix model which calculates a set of textural parameters for image classification. This co-occurrence matrix model examines the statistics of the spatial relationship between gray levels in a homogeneously textured image with calculated textural features which represent measures such as homogeneity and contrast. The method of the present invention uses this model to construct a set of normalized textural parameters from the textural parameters and calculates a value for the normalized textural parameters from this set, where the normalized textural parameters are related to the physical properties of the surface, such as pile lay of a carpet. The method compares the value for each of the normalized textural parameters of an unknown sample to the value for each of the corresponding normalized textural parameters for a known, or goal, sample. In one embodiment, the method compares an unknown sample of a saxony-type carpet to a goal sample of a saxony-type carpet having a tightly tailored surface texture to determine whether the unknown sample is such a carpet.

    摘要翻译： 本发明广泛地涉及用于分析表面纹理的图像分析方法，以及以该方法为特征的具有紧密定制的表面纹理的萨克森型地毯。 该方法采用基于二阶共生矩阵模型的模型，该模型计算图像分类的一组纹理参数。 该共生矩阵模型检查均匀纹理图像中的灰度级之间的空间关系的统计，其中计算的纹理特征表示诸如均匀性和对比度的度量。 本发明的方法使用该模型从结构参数构建一组归一化的结构参数，并从该组计算出归一化结构参数的值，其中标准化的结构参数与表面的物理性质相关， 作为地毯的堆叠。 该方法将未知样本的每个标准化结构参数的值与针对已知或目标样本的每个相应的归一化纹理参数的值进行比较。 在一个实施例中，该方法将萨克森型地毯的未知样品与具有紧密定制的表面纹理的萨克森型地毯的目标样品进行比较，以确定未知样品是否为这样的地毯。