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

US08532949B2 Computer-implemented methods and systems for classifying defects on a specimen 有权
标题翻译：用于对样品上的缺陷进行分类的计算机实现的方法和系统
公开(公告)号：US08532949B2
公开(公告)日：2013-09-10
申请号：US11249144
申请日：2005-10-12
申请人： Cho Huak Teh , Tommaso Torelli , Dominic David , Chiuman Yeung , Michael Gordon Scott , Lalita A. Balasubramanian , Lisheng Gao , Tong Huang , Jianxin Zhang , Michal Kowalski , Jonathan Oakley
发明人： Cho Huak Teh , Tommaso Torelli , Dominic David , Chiuman Yeung , Michael Gordon Scott , Lalita A. Balasubramanian , Lisheng Gao , Tong Huang , Jianxin Zhang , Michal Kowalski , Jonathan Oakley
IPC分类号： G01N37/00
CPC分类号： G01N21/9501 , G06T7/0004 , G06T2207/30148
摘要： Various computer-implemented methods for classifying defects on a specimen are provided. One method includes assigning individual defects detected on the specimen to defect groups based on one or more characteristics of the individual defects. The method also includes displaying information about the defect groups to a user. In addition, the method includes allowing the user to assign a classification to each of the defect groups. Systems configured to classify defects on a specimen are also provided. One system includes program instructions executable on a processor for assigning individual defects detected on the specimen to defect groups based on one or more characteristics of the individual defects. The system also includes a user interface configured for displaying information about the defect groups to a user and allowing the user to assign a classification to each of the defect groups.
摘要翻译：提供了用于对样本上的缺陷进行分类的各种计算机实现的方法。一种方法包括基于单个缺陷的一个或多个特征将在样本上检测到的各个缺陷分配给缺陷组。该方法还包括向用户显示关于缺陷组的信息。此外，该方法包括允许用户为每个缺陷组分配分类。还提供了配置为对样品上的缺陷进行分类的系统。一个系统包括可在处理器上执行的程序指令，用于基于单个缺陷的一个或多个特征将在样本上检测到的各个缺陷分配给缺陷组。该系统还包括被配置为向用户显示关于缺陷组的信息的用户界面，并允许用户为每个缺陷组分配分类。

2. 发明申请

US20060082763A1 Computer-implemented methods and systems for classifying defects on a specimen 有权
公开(公告)号：US20060082763A1
公开(公告)日：2006-04-20
申请号：US11249144
申请日：2005-10-12
申请人： Cho Teh , Tommaso Torelli , Dominic David , Chiuman Yeung , Michael Scott , Lalita Balasubramanian , Lisheng Gao , Tong Huang , Jianxin Zhang , Michal Kowalski , Jonathan Oakley
发明人： Cho Teh , Tommaso Torelli , Dominic David , Chiuman Yeung , Michael Scott , Lalita Balasubramanian , Lisheng Gao , Tong Huang , Jianxin Zhang , Michal Kowalski , Jonathan Oakley
IPC分类号： G01N21/00 , H01J3/14
CPC分类号： G01N21/9501 , G06T7/0004 , G06T2207/30148
摘要： Various computer-implemented methods for classifying defects on a specimen are provided. One method includes assigning individual defects detected on the specimen to defect groups based on one or more characteristics of the individual defects. The method also includes displaying information about the defect groups to a user. In addition, the method includes allowing the user to assign a classification to each of the defect groups. Systems configured to classify defects on a specimen are also provided. One system includes program instructions executable on a processor for assigning individual defects detected on the specimen to defect groups based on one or more characteristics of the individual defects. The system also includes a user interface configured for displaying information about the defect groups to a user and allowing the user to assign a classification to each of the defect groups.

3. 发明申请

US20060265145A1 FLEXIBLE HYBRID DEFECT CLASSIFICATION FOR SEMICONDUCTOR MANUFACTURING 有权
标题翻译：用于半导体制造的灵活混合缺陷分类
公开(公告)号：US20060265145A1
公开(公告)日：2006-11-23
申请号：US10954968
申请日：2004-09-30
申请人： Patrick Huet , Maruti Shanbhag , Sandeep Bhagwat , Michal Kowalski , Vivekanand Kini , David Randall , Sharon McCauley , Tong Huang , Jianxin Zhang , Kenong Wu , Lisheng Gao , Ariel Tribble , Ashok Kulkarni , Cecelia Anne Campochiaro
发明人： Patrick Huet , Maruti Shanbhag , Sandeep Bhagwat , Michal Kowalski , Vivekanand Kini , David Randall , Sharon McCauley , Tong Huang , Jianxin Zhang , Kenong Wu , Lisheng Gao , Ariel Tribble , Ashok Kulkarni , Cecelia Anne Campochiaro
IPC分类号： G01B5/28
CPC分类号： G06T7/0004 , G01R31/2846 , G06T2200/24 , G06T2207/30148
摘要： Hybrid methods for classifying defects in semiconductor manufacturing are provided. The methods include applying a flexible sequence of rules for defects to inspection data. The sequence of rules includes deterministic rules, statistical rules, hybrid rules, or some combination thereof. The rules included in the sequence may be selected by a user using a graphical interface The method also includes classifying the defects based on results of applying the sequence of rules to the inspection data.
摘要翻译：提供了用于分类半导体制造中的缺陷的混合方法。这些方法包括将错误的规则序列应用于检查数据。规则序列包括确定性规则，统计规则，混合规则或其某种组合。包括在序列中的规则可以由用户使用图形界面来选择。该方法还包括基于将规则序列应用于检查数据的结果对缺陷进行分类。

4. 发明授权

US07142992B1 Flexible hybrid defect classification for semiconductor manufacturing 有权
标题翻译：用于半导体制造的灵活混合缺陷分类
公开(公告)号：US07142992B1
公开(公告)日：2006-11-28
申请号：US10954968
申请日：2004-09-30
申请人： Patrick Huet , Maruti Shanbhag , Sandeep Bhagwat , Michal Kowalski , Vivekanand Kini , David Randall , Sharon McCauley , Tong Huang , Jianxin Zhang , Kenong Wu , Lisheng Gao , Ariel Tribble , Ashok Kulkarni , Cecelia Anne Campochiaro
发明人： Patrick Huet , Maruti Shanbhag , Sandeep Bhagwat , Michal Kowalski , Vivekanand Kini , David Randall , Sharon McCauley , Tong Huang , Jianxin Zhang , Kenong Wu , Lisheng Gao , Ariel Tribble , Ashok Kulkarni , Cecelia Anne Campochiaro
IPC分类号： G01R31/00 , G06F19/00
CPC分类号： G06T7/0004 , G01R31/2846 , G06T2200/24 , G06T2207/30148
摘要： Hybrid methods for classifying defects in semiconductor manufacturing are provided. The methods include applying a flexible sequence of rules for defects to inspection data. The sequence of rules includes deterministic rules, statistical rules, hybrid rules, or some combination thereof. The rules included in the sequence may be selected by a user using a graphical interface. The method also includes classifying the defects based on results of applying the sequence of rules to the inspection data.
摘要翻译：提供了用于分类半导体制造中的缺陷的混合方法。这些方法包括将错误的规则序列应用于检查数据。规则序列包括确定性规则，统计规则，混合规则或其某种组合。序列中包括的规则可以由用户使用图形界面来选择。该方法还包括基于将规则序列应用于检查数据的结果对缺陷进行分类。

5. 发明授权

US07359544B2 Automatic supervised classifier setup tool for semiconductor defects 有权
标题翻译：用于半导体缺陷的自动监控分类器设置工具
公开(公告)号：US07359544B2
公开(公告)日：2008-04-15
申请号：US10713628
申请日：2003-11-13
申请人： Lisheng Gao , Bo Magluyan , Jianxin Zhang , Kevin Yeung , Kenong Wu , Tong Huang
发明人： Lisheng Gao , Bo Magluyan , Jianxin Zhang , Kevin Yeung , Kenong Wu , Tong Huang
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G06K9/6253 , G06T7/0004
摘要： Disclosed are methods and apparatus for efficiently setting up and maintaining a defect classification system. In general terms, the setup procedure optionally includes automatically grouping a set of provided defects and presenting a representative set from each defect group to the user for classification. After the initial manual classification of the representative defects, the setup procedure includes an automatic procedure for classifying the non-reviewed or unclassified defects based on the manual class codes from the user-reviewed defects. After the automatic classification operation, the user may also be presented with defects from each class which may require re-classification. In particular embodiments, the user is iteratively presented with defects which have classifications that are suspect, which are near classification boundaries, or have classifications that have a low confidence level until each class is pure or contains a same type of defect classes as assigned by the user.
摘要翻译：公开了用于有效地建立和维护缺陷分类系统的方法和装置。一般来说，设置过程可选地包括自动地对一组提供的缺陷进行分组，并将来自每个缺陷组的代表集合给用户进行分类。在对代表性缺陷进行初步手动分类后，安装步骤包括根据用户审查缺陷的手册类代码分类未经审查或未分类的缺陷的自动程序。在自动分类操作之后，用户也可能会出现每个类别可能需要重新分类的缺陷。在特定实施例中，用户被迭代地呈现具有可疑的分类的缺陷，其接近分类边界，或者具有低置信度水平的分类，直到每个类是纯的或包含由所分配的相同类型的缺陷类别用户。

6. 发明申请

US20060077656A1 Illumination for working machines 审中-公开
标题翻译：工作机器的照明
公开(公告)号：US20060077656A1
公开(公告)日：2006-04-13
申请号：US11247131
申请日：2005-10-12
申请人： Tong Huang
发明人： Tong Huang
IPC分类号： F21L4/00
CPC分类号： F21V21/096 , F21V21/32 , F21W2131/403 , F21Y2115/10
摘要： An illumination for working machine of the preferred embodiment of the present invention comprises: a LED light portion that is a casing has a lampshade, a lens, a circuit board and a LED light therein one end and has cave on the other end of the casing. There is a battery set in the casing also to provide the power for the LED light. A adjust portion is a long tube that made by soft material. The adjust portion can be bended to any angle and fixed at that angle. One end of the adjust portion connects to the LED light portion and the other end of the adjust portion has a connecting set thereof. A fix portion has a screw hole at one end and has a pit at the other end with a magnet therein. The adjust portion screws to the fix portion with the threaded section.
摘要翻译：本发明优选实施例的工作机的照明包括：作为壳体的LED灯部分，其一端具有灯罩，透镜，电路板和LED灯，并且在壳体的另一端具有洞穴。外壳中还有一个电池组，为LED灯提供电源。调节部是由软质材料制成的长管。调节部分可以弯曲成任何角度并以该角度固定。调节部分的一端连接到LED灯部分，并且调节部分的另一端具有连接组件。固定部分在一端具有螺孔，另一端具有一个位于其中的磁体的凹坑。调整部分用螺纹部分固定在固定部分上。

7. 发明授权

US07570797B1 Methods and systems for generating an inspection process for an inspection system 有权
标题翻译：生成检查系统检查过程的方法和系统
公开(公告)号：US07570797B1
公开(公告)日：2009-08-04
申请号：US11125429
申请日：2005-05-10
申请人： David Wang , Patrick Huet , Tong Huang , Martin Plihal , Adam Chien-Huei Chen , Mike Van Riet , Stewart Hill
发明人： David Wang , Patrick Huet , Tong Huang , Martin Plihal , Adam Chien-Huei Chen , Mike Van Riet , Stewart Hill
IPC分类号： G06K9/00
CPC分类号： G06K9/6253 , G01N21/9501 , G06K2209/19 , G06T7/0004 , G06T2200/24 , G06T2207/10152 , G06T2207/20081 , G06T2207/30148
摘要： Methods and systems for generating an inspection process for an inspection system are provided. One computer implemented method includes generating inspection data for a selected defect on a specimen at different values of one or more image acquisition parameters of the inspection system. The method also includes determining which of the different values produces the best inspection data for the selected defect. In addition, the method includes selecting the different values determined to produce the best inspection data as values of the one or more image acquisition parameters to be used for the inspection process.
摘要翻译：提供了用于产生检查系统的检查过程的方法和系统。一种计算机实现的方法包括在检查系统的一个或多个图像采集参数的不同值处产生用于样本上的选定缺陷的检查数据。该方法还包括确定哪个不同的值产生用于所选缺陷的最佳检查数据。此外，该方法包括选择确定为产生最佳检查数据的不同值作为要用于检查过程的一个或多个图像获取参数的值。

8. 发明申请

US20210300649A1 COTTON BALER 有权
公开(公告)号：US20210300649A1
公开(公告)日：2021-09-30
申请号：US16895536
申请日：2020-06-08
申请人： Tong Huang , Yaoqing Xiong , Yuanli Lyu
发明人： Tong Huang , Yaoqing Xiong , Yuanli Lyu
IPC分类号： B65D65/14 , B65H18/28
摘要： The invention uses a new system which cuts and unlocks a wrapping material (PE film) for cotton in a continuous manner in cotton harvesting, and a new method in production of such film. The film consists of many segments that make many bales of cotton. The film is separated with perforation by laser or other methods. A double sided adhesive is used to glue the bale at the end of it, which is covered by a folded bridge. The bridge connects the both ends of the segments of the film. When perforated film is torn at a signal by the harvest machine, the bridge is unfolded as a leading edge for the next segment after a brief bridge linkage of both segments. The way of folding the bridge is key part of the invention, which accurately uncovers the end adhesive for the new bale and reduces the problem of tangling of the film at the time of separation.

9. 发明授权

US07313841B2 Suspendable magnetic brush for cleaning an aquarium with a curved window surface 失效
标题翻译：用于清洁具有弯曲窗口表面的水族箱的可悬挂磁刷
公开(公告)号：US07313841B2
公开(公告)日：2008-01-01
申请号：US10528257
申请日：2002-09-29
申请人： Tong Huang
发明人： Tong Huang
IPC分类号： A01K63/04 , A47L1/12
CPC分类号： A01K63/10
摘要： Present invention relates a suspendable magnetic brush for cleaning an aquarium with curved window surface, characterized in that an upper cover with an air chamber is attached tightly to a bottom cover with a cleaning material layer underneath, and an inner cover with a magnet located therein is provided inside the air chamber, said inner cover being attached to the bottom cover while isolated from the air chamber. Said upper cover having through holes connecting the air chamber to the exterior of the device. It is possible to adjust the air or liquid in the air chamber through the holes connecting the upper cover and the air chamber so that the weight of the interior magnetic brush can be adjusted so as to balance all the forces exerted upon the interior magnetic brush. As a result the interior elements of the brush can suspend in the water and move smoothly on the aquarium window upon the manipulation of the exterior brush. With the convex edge(s) of the bottom cover matching the curved window surface of the aquarium the magnetic brush can clean both curved window surface and the planar window surface as well.
摘要翻译：本发明涉及一种用于清洁具有弯曲窗口表面的水族箱的可悬挂磁刷，其特征在于具有空气室的上盖紧紧地附着在底盖下面，其下面具有清洁材料层，并且具有位于其中的磁体的内盖是设置在空气室内部，所述内盖在与空气室隔离的同时附接到底盖。所述上盖具有将空气室连接到装置的外部的通孔。可以通过连接上盖和空气室的孔来调节空气室中的空气或液体，使得可以调节内部磁刷的重量，以平衡施加在内部磁刷上的所有力。结果，刷子的内部元件可以悬挂在水中并且在外部刷子的操纵时在水族箱窗口上平稳移动。由于底盖的凸缘与水族箱的弯曲窗表面相匹配，磁刷也可以清洁曲面窗表面和平面窗表面。

10. 发明授权

US08014973B1 Distance histogram for nearest neighbor defect classification 有权
标题翻译：最近相邻缺陷分类的距离直方图
公开(公告)号：US08014973B1
公开(公告)日：2011-09-06
申请号：US12202251
申请日：2008-08-30
申请人： Tong Huang
发明人： Tong Huang
IPC分类号： G06F19/00
CPC分类号： G06K9/6276 , Y10S707/99935
摘要： A method for constructing a distance histogram for nearest neighbor classification. A training sample is determined for each of two classes. For each defect, a distance is measured in the feature space between the defect and the training sample for each of the classes. All of the distances for a given defect are normalized by dividing each distance for the given defect by the sum of all of the distances for the given defect. A histogram is constructed by plotting a chart of the normalized distances versus the number of defects having the distances. A threshold bar is placed on the center of the histogram to construct a normal nearest neighbor classifier. The threshold bar can be adjusted to the left or to the right to construct a weighted nearest neighbor classifier.
摘要翻译：一种用于构造最近邻分类的距离直方图的方法。确定两个类别中的每一个的培训样本。对于每个缺陷，在每个类别的缺陷和训练样本之间的特征空间中测量距离。给定缺陷的所有距离通过将给定缺陷的每个距离除以给定缺陷的所有距离的总和来进行归一化。通过绘制归一化距离的图表与具有距离的缺陷数量来构建直方图。阈值条放置在直方图的中心以构建正常最近邻分类器。阈值条可以向左或向右调整以构建加权最近邻分类器。

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