专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08280939B2 Methods and apparatus for automatic accuracy-sustaining scaling of block-floating-point operands 有权
标题翻译：块浮点运算的自动精度维持缩放的方法和装置
公开(公告)号：US08280939B2
公开(公告)日：2012-10-02
申请号：US12125536
申请日：2008-05-22
申请人： Igor Reyzin , Aleksey Lipchin
发明人： Igor Reyzin , Aleksey Lipchin
IPC分类号： G06F7/483
CPC分类号： G06F7/483 , G06F2207/3824
摘要： A computer-implemented method performs an operation on a set of at least one BFP operands to generate a BFP result. The method is designed to reduce the risks of overflow and loss of accuracy attributable to the operation. The method performs an analysis to determine respective shift values for each of the operands and the result. The method calculates result mantissas by shifting the stored bit patterns representing the corresponding operand mantissa values by their respective associated shift values determined in the analysis step, performing the operation on shifted operand mantissas to generate preliminary result mantissa, and shifting the preliminary result mantissas by a number of bits determined in the analysis step.
摘要翻译：计算机实现的方法对一组至少一个BFP操作数执行操作以产生BFP结果。该方法旨在减少由于操作引起的溢出和精度损失的风险。该方法执行分析以确定每个操作数和结果的各个移位值。该方法通过将表示相应的操作数尾数值的所存储的位模式移动其分析步骤中确定的各自相关的移位值来计算结果尾数，对移位的操作数尾进行操作以产生初步结果尾数，并将初步结果尾数移位在分析步骤中确定的位数。

2. 发明申请

US20090244291A1 DYNAMIC OBJECT CLASSIFICATION 有权
标题翻译：动态对象分类
公开(公告)号：US20090244291A1
公开(公告)日：2009-10-01
申请号：US12397287
申请日：2009-03-03
申请人： Mahesh Saptharishi , Dimitri A. Lisin , Aleksey Lipchin , Igor Reyzin
发明人： Mahesh Saptharishi , Dimitri A. Lisin , Aleksey Lipchin , Igor Reyzin
IPC分类号： H04N17/00 , H04N5/335 , G06K9/62
CPC分类号： G06K9/00536 , G06K9/00718 , G06K9/00771 , G06K9/4671 , G06K9/52 , G06K9/6201 , G06T7/246 , G06T2207/10016 , G06T2207/30232 , H04N5/23203 , H04N5/23219 , H04N5/23293 , H04N7/18 , H04N7/181
摘要： A camera system comprises an image capturing device and an object classification module connected to the image capturing device. The image capturing device has a field of view and produces image data representing an image of the field of view. The object classification module is operable to determine whether or not an object in an image is a member of an object class. The object classification module includes N decision steps configured in a cascade configuration, wherein at least one of the N decision steps is operable to (a) accept an object as a member of the object class, (b) reject an object as a member of the object class, and (c) call on a next step to determine whether or not an object is a member of the object class.
摘要翻译：相机系统包括图像拍摄装置和连接到图像捕获装置的对象分类模块。图像捕获装置具有视野并产生表示视场图像的图像数据。对象分类模块可操作以确定图像中的对象是否是对象类的成员。对象分类模块包括在级联配置中配置的N个判定步骤，其中N个判定步骤中的至少一个可操作以（a）接受作为对象类的成员的对象，（b）拒绝作为对象类，（c）调用下一步来确定对象是否是对象类的成员。

3. 发明授权

US08934709B2 Dynamic object classification 有权
标题翻译：动态对象分类
公开(公告)号：US08934709B2
公开(公告)日：2015-01-13
申请号：US12397287
申请日：2009-03-03
申请人： Mahesh Saptharishi , Dimitri A. Lisin , Aleksey Lipchin , Igor Reyzin
发明人： Mahesh Saptharishi , Dimitri A. Lisin , Aleksey Lipchin , Igor Reyzin
IPC分类号： G06K9/62 , G06K9/68 , H04N5/232 , G06K9/00 , G06T7/20
CPC分类号： G06K9/00536 , G06K9/00718 , G06K9/00771 , G06K9/4671 , G06K9/52 , G06K9/6201 , G06T7/246 , G06T2207/10016 , G06T2207/30232 , H04N5/23203 , H04N5/23219 , H04N5/23293 , H04N7/18 , H04N7/181
摘要： A camera system comprises an image capturing device and an object classification module connected to the image capturing device. The image capturing device has a field of view and produces image data representing an image of the field of view. The object classification module is operable to determine whether an object in an image is a member of an object class. The object classification module includes N decision steps configured in a cascade configuration, wherein at least one of the N decision steps is operable to (a) accept an object as a member of the object class, (b) reject an object as a member of the object class, and (c) call on a next step to determine whether an object is a member of the object class.
摘要翻译：相机系统包括图像拍摄装置和连接到图像捕获装置的对象分类模块。图像捕获装置具有视野并产生表示视场图像的图像数据。对象分类模块可操作以确定图像中的对象是否是对象类的成员。对象分类模块包括在级联配置中配置的N个判定步骤，其中N个判定步骤中的至少一个可操作以（a）接受作为对象类的成员的对象，（b）拒绝作为对象类，以及（c）调用下一步来确定对象是否是对象类的成员。

4. 发明申请

US20090292750A1 METHODS AND APPARATUS FOR AUTOMATIC ACCURACY- SUSTAINING SCALING OF BLOCK-FLOATING-POINT OPERANDS 有权
标题翻译：方法和装置，用于自动精度保持平移点操作的调整
公开(公告)号：US20090292750A1
公开(公告)日：2009-11-26
申请号：US12125536
申请日：2008-05-22
申请人： Igor Reyzin , Aleksey Lipchin
发明人： Igor Reyzin , Aleksey Lipchin
IPC分类号： G06F17/10 , G06F5/01
CPC分类号： G06F7/483 , G06F2207/3824
摘要： A computer-implemented method performs an operation on a set of at least one BFP operands to generate a BFP result. The method is designed to reduce the risks of overflow and loss of accuracy attributable to the operation. The method performs an analysis to determine respective shift values for each of the operands and the result. The method calculates result mantissas by shifting the stored bit patterns representing the corresponding operand mantissa values by their respective associated shift values determined in the analysis step, performing the operation on shifted operand mantissas to generate preliminary result mantissa, and shifting the preliminary result mantissas by a number of bits determined in the analysis step.
摘要翻译：计算机实现的方法对一组至少一个BFP操作数执行操作以产生BFP结果。该方法旨在减少由于操作引起的溢出和精度损失的风险。该方法执行分析以确定每个操作数和结果的各个移位值。该方法通过将表示相应的操作数尾数值的所存储的位模式移动其分析步骤中确定的各自相关的移位值来计算结果尾数，对移位的操作数尾进行操作以产生初步结果尾数，并将初步结果尾数移位在分析步骤中确定的位数。

5. 发明授权

US06215915B1 Image processing methods and apparatus for separable, general affine transformation of an image 失效
标题翻译：用于图像的可分离，一般仿射变换的图像处理方法和装置
公开(公告)号：US06215915B1
公开(公告)日：2001-04-10
申请号：US09027432
申请日：1998-02-20
申请人： Igor Reyzin
发明人： Igor Reyzin
IPC分类号： G06K932
CPC分类号： G06T3/00
摘要： A separable, general affine transformation according to the invention permits an image to be concurrently rotated, scaled, translated, skewed, sheared, or otherwise transformed via a sequence of one-dimensional transformations. A general affine transformation of an image in two dimensions is achieved by generating an “intermediate” image via affine transformation of the source along a first axis. The intermediate image is then subjected to affine transformation along a second axis, e.g., perpendicular to the first. The resultant image may be used in place of that which would be produced by a single two-dimensional transformation of the source image (e.g., in a single pass).
摘要翻译：根据本发明的可分离的一般仿射变换允许图像被同时旋转，缩放，平移，倾斜，剪切或以其它方式通过一维变换序列变换。通过沿着第一轴的仿射变换生成“中间”图像来实现二维图像的一般仿射变换。然后，中间图像沿着第二轴进行仿射变换，例如垂直于第一轴。可以使用所得到的图像来代替通过源图像的单个二维变换（例如，单次通过）产生的图像。

6. 发明授权

US6064388A Cartesian to polar coordinate transformation 失效
标题翻译：笛卡尔坐标转换为极坐标
公开(公告)号：US6064388A
公开(公告)日：2000-05-16
申请号：US967683
申请日：1997-11-10
申请人： Igor Reyzin
发明人： Igor Reyzin
IPC分类号： G06F7/548 , G06T15/00
CPC分类号： G06F7/548
摘要： In an improved Cartesian to polar coordinate transformation, a Cartesian system of discrete data elements is converted to a polar system of discrete data elements. Each Cartesian element is divided into subelements and one of the subelements is designated as the polar system origin. A polar system comprising an intersecting plurality of radial sector lines and a plurality of confocal arcs formed of the subelements is defined about the origin. The lines and arcs define boundaries of polar data elements. The subelements lying within the polar element boundaries are identified and their respective data values are derived from the data values of corresponding Cartesian elements. Polar element data values are calculated based on the data values of the subelements contributing to the polar element. The present transformation technique offers the advantage of few floating point operations and provides a computationally efficient conversion system readily adaptive to changes in system parameters.
摘要翻译：在改进的直角坐标到极坐标变换中，将离散数据元素的笛卡尔系统转换为离散数据元素的极坐标系。每个笛卡尔元素被分为子元素，其中一个子元素被指定为极系统原点。围绕原点定义包括相交的多个径向扇形线和由子元件形成的多个共焦弧的极坐标系。线和弧定义极数数据元素的边界。识别位于极性元素边界内的子元素，并且它们各自的数据值是从相应笛卡尔元素的数据值导出的。基于有助于极性元素的子元素的数据值计算极值元素数据值。目前的转换技术提供了少量浮点运算的优点，并提供了一种易于适应系统参数变化的计算效率高的转换系统。

7. 发明授权

US06381375B1 Methods and apparatus for generating a projection of an image 失效
标题翻译：用于产生图像的投影的方法和装置
公开(公告)号：US06381375B1
公开(公告)日：2002-04-30
申请号：US09055543
申请日：1998-04-06
申请人： Igor Reyzin
发明人： Igor Reyzin
IPC分类号： G06K936
CPC分类号： G06T3/00
摘要： Novel methods for generating a projection of an image according to the invention concurrently rotate, scale, translate, skew, shear, or otherwise transform the image via a sequence of two one-dimensional transformations. A first intermediate image is generated via affine transformation of the source along a first axis. The intermediate image is then subjected to affine transformation along a second axis, e.g., perpendicular to the first. A projection of the resultant image is generated along a selected one of the first or second axes by summing pixel intensities in corresponding rows (or columns) or by summing counts of pixels whose intensities are above or below a threshold.
摘要翻译：用于产生根据本发明的图像的投影的新颖方法通过两个一维变换的序列同时旋转，缩放，平移，偏斜，剪切或以其它方式变换图像。通过源沿着第一轴的仿射变换产生第一中间图像。然后，中间图像沿着第二轴进行仿射变换，例如垂直于第一轴。通过将相应行（或列）中的像素强度相加或通过对其强度高于或低于阈值的像素的计数相加来沿着所选择的第一或第二轴中的一个生成图像的投影。

8. 发明授权

US06718074B1 Method and apparatus for inspection for under-resolved features in digital images 失效
标题翻译：数字图像中未解决特征的检查方法和装置
公开(公告)号：US06718074B1
公开(公告)日：2004-04-06
申请号：US09585633
申请日：2000-06-02
申请人： Paul Dutta-Choudhury , Joe Scola , Brad Safford , Igor Reyzin
发明人： Paul Dutta-Choudhury , Joe Scola , Brad Safford , Igor Reyzin
IPC分类号： G06K900
CPC分类号： G06T7/0012 , G06T3/403 , G06T7/0004
摘要： A machine vision inspection system and method that increase the resolution of object image-data without physically manipulating the physical optics of cameras used during inspection. The exemplary embodiment of the invention provides a system and method that perform what may be characterized as a digital zoom. Using this digital zoom, the resolution of object image-data provided by a camera may be artificially increased. Moreover, in accordance with the exemplary embodiment of the invention, a determination may be made regarding whether portions of the object image-data are under-resolved, and based on that determination, a local digital zoom may be performed on that under-resolved portion of object image-data to increase the resolution of that portion of object image-data. Additionally, the resulting portion of the object image-data with increased image resolution may be scaled-back, such that the portion of increased resolution object image-data may be combined with the other object image-data to provide a faithful, scaled representation of the original sample-object and/or sample-object feature.
摘要翻译：一种机器视觉检查系统和方法，可以在物理上操纵检查期间使用的相机的物理光学元件，增加对象图像数据的分辨率。本发明的示例性实施例提供了执行可以被表征为数字变焦的系统和方法。使用该数字变焦，可以人为地增加由相机提供的对象图像数据的分辨率。此外，根据本发明的示例性实施例，可以确定对象图像数据的部分是否未被分解，并且基于该确定，可以对未解决部分执行局部数字变焦的对象图像数据，以增加该部分对象图像数据的分辨率。另外，具有增加的图像分辨率的对象图像数据的所得部分可以缩小，使得增加的分辨率对象图像数据的部分可以与其他对象图像数据组合以提供忠实的，缩放的原始样本对象和/或样本对象特征。

9. 发明授权

US06421458B2 Automated inspection of objects undergoing general affine transformation 有权
标题翻译：对进行一般仿射变换的物体进行自动检查
公开(公告)号：US06421458B2
公开(公告)日：2002-07-16
申请号：US09141932
申请日：1998-08-28
申请人： David J. Michael , Igor Reyzin
发明人： David J. Michael , Igor Reyzin
IPC分类号： G06K932
CPC分类号： G06K9/00 , G06T7/001 , G06T7/33 , G06T2207/30108
摘要： During statistical training and automated inspection of objects by a machine vision system, a General Affine Transform is advantageously employed to improve system performance. During statistical training, the affine poses of a plurality of training images are determined with respect to an alignment model image. Following filtering to remove high frequency content, the training images and their corresponding affine poses are applied to an affine transformation. The resulting transformed images are accumulated to compute template and threshold images to be used for run-time inspection. During run-time inspection, the affine pose of the run-time image relative to the alignment model image is determined. Following filtering of the run-time image, the run-time image is affine transformed by its affine pose. The resulting transform image is compared with the template and threshold images computed during statistical training to determine object status. In this manner, automated training and inspection is relatively less demanding on system storage, and results in an improvement in system speed and accuracy.
摘要翻译：在通过机器视觉系统的统计训练和物体的自动检查期间，有利地采用通用仿射变换来提高系统性能。在统计训练期间，相对于对准模型图像确定多个训练图像的仿射姿态。进行滤波以去除高频内容后，将训练图像及其对应的仿射姿态应用于仿射变换。累积所得到的变换图像以计算用于运行时检查的模板和阈值图像。在运行时检查期间，确定运行时图像相对于对准模型图像的仿射姿态。在运行时图像过滤之后，运行时图像通过其仿射姿态进行仿射变换。将所得到的变换图像与在统计训练期间计算的模板和阈值图像进行比较，以确定对象状态。以这种方式，自动化培训和检查对系统存储的要求相对较低，并且导致系统速度和精度的提高。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式