公开(公告)号：US20070154108A1

公开(公告)日：2007-07-05

申请号：US11685338

申请日：2007-03-13

申请人： Lawrence Albertelli ,  David Ii ,  Nina Kung

发明人： Lawrence Albertelli ,  David Ii ,  Nina Kung

IPC分类号： G06K9/38

CPC分类号： G06K9/38 ,  G06K2209/01

摘要： In order to render information contained in images more detectable in the presence of noise, the present invention discloses a system and method to binarize the images in the presence of noise. The method of this invention comprises the steps of applying a dynamic range reducing filter to the digitized image values, obtaining a range reduced image; applying an edge detecting filter to the range reduced image, obtaining a filtered image; and then, adaptively binarizing the digitized image utilizing the corresponding filtered image to obtain an adaptive threshold.

摘要翻译： 为了在存在噪声的情况下使包含在图像中的信息更可检测，本发明公开了一种在存在噪声的情况下二值化图像的系统和方法。 本发明的方法包括以下步骤：对数字化图像值应用动态范围缩小滤波器，获得缩小后的图像; 将边缘检测滤波器应用于缩小后的图像，获得滤波图像; 然后利用相应的滤波图像自适应地二值化数字化图像以获得自适应阈值。

公开(公告)号：US20050207652A1

公开(公告)日：2005-09-22

申请号：US10804965

申请日：2004-03-19

申请人： Lawrence Albertelli ,  Nina Kung

发明人： Lawrence Albertelli ,  Nina Kung

IPC分类号： G06K9/32 ,  G06K9/48

CPC分类号： G06K9/3233 ,  G06K2209/01

摘要： A method and system for detecting the corners of a region in cluttered images. The initial data for the method of this invention includes an image of a region of interest. The edges interior to the region of interest are detected by an edge detection method. The detected edges are culled in order to obtain a reduced edge group, where the reduced edge group includes a number of points. A measure of cornerness is obtained for each one point from the reduced edge group. A number of candidate corner points are selected from the reduced edge group by applying a predetermined criterion to the measure of cornerness. The region corner points are identified from the candidate corner points based on a predetermined relationship, such as a distance, between each candidate corner point and characteristic edge points of the region of interest, such as edge centers and corners. The system implements the method of this invention.

摘要翻译： 用于检测杂乱图像中的区域的拐角的方法和系统。 本发明方法的初始数据包括感兴趣区域的图像。 通过边缘检测方法检测感兴趣区域内部的边缘。 检测到的边缘被淘汰以获得减少的边缘组，其中减少的边缘组包括多个点。 从减少边缘组的每个点获得角度的度量。 通过对角度的测量应用预定标准，从减少边缘组中选择多个候选角点。 基于每个候选角点与感兴趣区域的特征边缘点（例如边缘中心和拐角）之间的预定关系（例如距离），从候选角点识别区域角点。 该系统实现本发明的方法。

公开(公告)号：US20050275724A1

公开(公告)日：2005-12-15

申请号：US11196242

申请日：2005-08-04

申请人： Lawrence Albertelli

发明人： Lawrence Albertelli

IPC分类号： G01C21/02 ,  H04N1/00

CPC分类号： H04N1/00002 ,  H04N1/00018 ,  H04N1/00031 ,  H04N1/00045 ,  H04N1/00053 ,  H04N1/00063 ,  H04N2101/00

摘要： Resolution of an image capture system is measured by imaging a test target having a progression of feature sizes and pitch in respective sub-fields thereof. The image captured by the imaging system is then inspected to determine a sub-field image which does not include aliasing in the form of a Moire' pattern. Inclusion of reference numerals corresponding to the sub-field image feature size and pitch allows direct reading of the resolution of the imaging system. Such a system enables fast and accurate determination of the resolution and alignment of an imaging system using an inexpensively produced test target together with an arbitrary image viewing program.

摘要翻译： 通过对具有其各个子场中的特征尺寸和间距的进展的测试对象进行成像来测量图像拍摄系统的分辨率。 然后检查由成像系统捕获的图像以确定不包括以莫尔'图案形式的混叠的子场图像。 包含对应于子场图像特征尺寸和间距的附图标记允许直接读取成像系统的分辨率。 这样的系统能够使用廉价生产的测试目标以及任意的图像观看程序来快速且准确地确定成像系统的分辨率和对准。

公开(公告)号：US20050286772A1

公开(公告)日：2005-12-29

申请号：US10876175

申请日：2004-06-24

申请人： Lawrence Albertelli

发明人： Lawrence Albertelli

IPC分类号： G06K9/62

CPC分类号： G06K9/6292

摘要： Systems and methods are provided for classifying a subject into one of a plurality of output classes. An input pattern representing the subject is classified at a plurality of pattern recognition classifiers to obtain a ranked set of at least two classifier outputs at each classifier. A classifier output includes an associated output class, output score, and ranking. Each classifier output is mapped to a corresponding weight value according to its associated output class, output score, and ranking. The weight values for the classifier outputs are combined according to a voting algorithm to determine an output class associated with the subject.

摘要翻译： 提供了用于将受试者分类为多个输出类别之一的系统和方法。 表示被摄体的输入图案被分类为多个模式识别分类器，以在每个分类器处获得至少两个分类器输出的排列集合。 分类器输出包括相关的输出类，输出得分和排名。 每个分类器输出根据其相关的输出类别，输出分数和排名映射到相应的权重值。 分类器输出的权重值根据投票算法组合以确定与被摄体相关联的输出类别。