公开(公告)号：US08669523B2

公开(公告)日：2014-03-11

申请号：US13410506

申请日：2012-03-02

申请人： Chien-Huei Chen ,  Peter White ,  Michael J. Van Riet ,  Sankar Venkataraman ,  Hai Jiang ,  Hedong Yang ,  Ajay Gupta

发明人： Chien-Huei Chen ,  Peter White ,  Michael J. Van Riet ,  Sankar Venkataraman ,  Hai Jiang ,  Hedong Yang ,  Ajay Gupta

IPC分类号： H01J37/28 ,  G01N23/04 ,  G06T5/50

CPC分类号： H01J37/28 ,  G01N23/04 ,  G06T5/50 ,  G06T7/001 ,  G06T2207/30148 ,  H01J37/05 ,  H01J37/222 ,  H01J37/244

摘要： One embodiment relates to a method of inspecting a site location on a target substrate. Contours are obtained, the contours having been generated from a reference image using a design clip. A target image of the site location is acquired. The contours are aligned to the target image, and contrast values are computed for pixels on the contours. A threshold is applied to the contrast values to determine contour-based defect blobs. Another embodiment relates to a method of generating contours for use in inspecting a site location for defects. Other embodiments, aspects and features are also disclosed.

摘要翻译： 一个实施例涉及一种检查目标基板上的位置位置的方法。 获得轮廓，使用设计剪辑从参考图像生成轮廓。 获取站点位置的目标图像。 轮廓与目标图像对齐，并且对轮廓线上的像素计算对比度值。 将阈值应用于对比度值以确定基于轮廓的缺陷斑点。 另一个实施例涉及一种产生用于检查位置缺陷的轮廓的方法。 还公开了其它实施例，方面和特征。

公开(公告)号：US20100040263A1

公开(公告)日：2010-02-18

申请号：US12228739

申请日：2008-08-15

申请人： Wenjing Li ,  Sankar Venkataraman ,  Ulf Gustafsson ,  John Taylor Hargrove

发明人： Wenjing Li ,  Sankar Venkataraman ,  Ulf Gustafsson ,  John Taylor Hargrove

IPC分类号： A61B5/00

CPC分类号： G06T5/30 ,  G06T5/009 ,  G06T2207/30004 ,  G06T2207/30068

摘要： A method of contrast enhancement for improved visualization of diagnostically important tissue structures, such as blood vessels. A texture analysis algorithm is applied to identify regions with a high likelihood of disease. Mathematical morphology operations are applied to identify areas of high and low brightness (intensity). The low intensity areas are then subtracted, and controllably variable amounts of the high intensity areas are added, controlled by a selectable tuning parameter, to produce an image with controllably variable visualization enhancement.

摘要翻译： 一种对比度增强的方法，用于改善诊断上重要的组织结构如血管的可视化。 应用纹理分析算法识别疾病可能性高的地区。 应用数学形态学操作来识别高亮度和低亮度（强度）的区域。 然后减去低强度区域，并且通过可选择的调谐参数来控制可变量的高强度区域，以产生具有可控地可变的可视化增强的图像。

公开(公告)号：US20100027863A1

公开(公告)日：2010-02-04

申请号：US12221328

申请日：2008-08-01

申请人： Sankar Venkataraman ,  Wenjing Li ,  Ulf Peter Gustafsson

发明人： Sankar Venkataraman ,  Wenjing Li ,  Ulf Peter Gustafsson

IPC分类号： A61B5/00

CPC分类号： A61B5/02007 ,  A61B1/00009 ,  A61B5/0084 ,  G06T7/0012 ,  G06T7/11 ,  G06T2207/30096 ,  G06T2207/30101

摘要： The present invention discloses a method for the detection of atypical vessels in digital cervical imagery. A pre-processing stage is applied to enhance the contrast of blood vessel features compared to the surrounding tissue. Next, a segmentation stage is applied to identify regions of interest for atypical vessels using texture and gradient information. Finally, a post-processing stage (1) identifies other clinically relevant features in the cervical imager, and removes these features from the region of interest; and (2) uses color, size, and shape information to further refine the region of interest to eliminate false positives and determine a final region of interest. This automated method of atypical vessel detection is especially useful for diagnostic purposes such as cervical cancer detection.

摘要翻译： 本发明公开了一种检测数字宫颈图像中非典型血管的方法。 应用预处理阶段来增强与周围组织相比的血管特征的对比度。 接下来，使用分割阶段来使用纹理和梯度信息来识别非典型血管的感兴趣区域。 最后，后处理阶段（1）识别子宫颈成像仪中的其他临床相关特征，并从感兴趣区域中去除这些特征; 和（2）使用颜色，大小和形状信息进一步细化感兴趣的区域以消除假阳性，并确定最终感兴趣的区域。 这种非典型血管检测的自动化方法对于诸如宫颈癌检测的诊断目的尤其有用。

公开(公告)号：US08351667B2

公开(公告)日：2013-01-08

申请号：US12228739

申请日：2008-08-15

申请人： Wenjing Li ,  Sankar Venkataraman ,  Ulf Gustafsson ,  John Taylor Hargrove

发明人： Wenjing Li ,  Sankar Venkataraman ,  Ulf Gustafsson ,  John Taylor Hargrove

IPC分类号： G06K9/18

CPC分类号： G06T5/30 ,  G06T5/009 ,  G06T2207/30004 ,  G06T2207/30068

摘要： A method of contrast enhancement for improved visualization of diagnostically important tissue structures, such as blood vessels. A texture analysis algorithm is applied to identify regions with a high likelihood of disease. Mathematical morphology operations are applied to identify areas of high and low brightness (intensity). The low intensity areas are then subtracted, and controllably variable amounts of the high intensity areas are added, controlled by a selectable tuning parameter, to produce an image with controllably variable visualization enhancement.

摘要翻译： 一种对比度增强的方法，用于改善诊断上重要的组织结构如血管的可视化。 应用纹理分析算法识别疾病可能性高的地区。 应用数学形态学操作来识别高亮度和低亮度（强度）的区域。 然后减去低强度区域，并且通过可选择的调谐参数来控制可变量的高强度区域，以产生具有可控地可变的可视化增强的图像。

公开(公告)号：US08090177B2

公开(公告)日：2012-01-03

申请号：US12221328

申请日：2008-08-01

申请人： Sankar Venkataraman ,  Wenjing Li ,  Ulf Peter Gustafsson

发明人： Sankar Venkataraman ,  Wenjing Li ,  Ulf Peter Gustafsson

IPC分类号： G06K9/00

CPC分类号： A61B5/02007 ,  A61B1/00009 ,  A61B5/0084 ,  G06T7/0012 ,  G06T7/11 ,  G06T2207/30096 ,  G06T2207/30101

摘要： The present invention discloses a method for the detection of atypical vessels in digital cervical imagery. A pre-processing stage is applied to enhance the contrast of blood vessel features compared to the surrounding tissue. Next, a segmentation stage is applied to identify regions of interest for atypical vessels using texture and gradient information. Finally, a post-processing stage (1) identifies other clinically relevant features in the cervical imager, and removes these features from the region of interest; and (2) uses color, size, and shape information to further refine the region of interest to eliminate false positives and determine a final region of interest. This automated method of atypical vessel detection is especially useful for diagnostic purposes such as cervical cancer detection.

摘要翻译： 本发明公开了一种检测数字宫颈图像中非典型血管的方法。 应用预处理阶段来增强与周围组织相比的血管特征的对比度。 接下来，使用分割阶段来使用纹理和梯度信息来识别非典型血管的感兴趣区域。 最后，后处理阶段（1）识别子宫颈成像仪中的其他临床相关特征，并从感兴趣区域中去除这些特征; 和（2）使用颜色，大小和形状信息进一步细化感兴趣的区域以消除假阳性，并确定最终感兴趣的区域。 这种非典型血管检测的自动化方法对于诸如宫颈癌检测的诊断目的尤其有用。