-
1.发明公开公开(公告)号：US20240005148A1
公开(公告)日：2024-01-04
申请号：US18103432
申请日：2023-01-30
申请人： Cognex Corporation
发明人： Lei Wang , Vivek Anand , Lowell D. Jacobson , David Y. Li
IPC分类号： G06N3/08 , G06V10/50 , G06F18/214 , G06V10/82 , G06V10/44
CPC分类号： G06N3/08 , G06V10/50 , G06F18/2148 , G06V10/7553 , G06V10/454 , G06V10/44 , G06V10/82
摘要： This invention provides a system and method for finding patterns in images that incorporates neural net classifiers. A pattern finding tool is coupled with a classifier that can be run before or after the tool to have labeled pattern results with sub-pixel accuracy. In the case of a pattern finding tool that can detect multiple templates, its performance is improved when a neural net classifier informs the pattern finding tool to work only on a subset of the originally trained templates. Similarly, in the case of a pattern finding tool that initially detects a pattern, a neural network classifier can then determine whether it has found the correct pattern. The neural network can also reconstruct/clean-up an imaged shape, and/or to eliminate pixels less relevant to the shape of interest, therefore reducing the search time, as well significantly increasing the chance of lock on the correct shapes.
-
公开(公告)号：US20210148694A1
公开(公告)日：2021-05-20
申请号：US17001018
申请日：2020-08-24
申请人： Cognex Corporation
发明人： David Y. Li , Li Sun , Lowell D. Jacobson , Lei Wang
摘要： This invention provides a system and method for selecting the correct profile from a range of peaks generated by analyzing a surface with multiple exposure levels applied at discrete intervals. The cloud of peak information is resolved by comparison to a model profile into a best candidate to represent an accurate representation of the object profile. Illustratively, a displacement sensor projects a line of illumination on the surface and receives reflected light at a sensor assembly at a set exposure level. A processor varies the exposure level setting in a plurality of discrete increments, and stores an image of the reflected light for each of the increments. A determination process combines the stored images and aligns the combined images with respect to a model image. Points from the combined images are selected based upon closeness to the model image to provide a candidate profile of the surface.
-
公开(公告)号：US10657650B2
公开(公告)日：2020-05-19
申请号：US16001885
申请日：2018-06-06
申请人： Cognex Corporation
发明人： Lei Wang , Vivek Anand , Lowell D. Jacobson
摘要： This invention provides a system and method for finding line features in an image that allows multiple lines to be efficiently and accurately identified and characterized. When lines are identified, the user can train the system to associate predetermined (e.g. text) labels with respect to such lines. These labels can be used to define neural net classifiers. The neural net operates at runtime to identify and score lines in a runtime image that are found using a line-finding process. The found lines can be displayed to the user with labels and an associated probability score map based upon the neural net results. Lines that are not labeled are generally deemed to have a low score, and are either not flagged by the interface, or identified as not relevant.
-
公开(公告)号：US11699283B2
公开(公告)日：2023-07-11
申请号：US17127889
申请日：2020-12-18
申请人： Cognex Corporation
发明人： Lei Wang , Vivek Anand , Lowell D. Jacobson
IPC分类号： G06T19/00 , G06T7/13 , G06T7/143 , G06V10/44 , G06V10/50 , G06V10/82 , G06F18/40 , G06F18/214 , G06F18/2415 , G06K9/62
CPC分类号： G06V10/82 , G06F18/2148 , G06F18/2415 , G06F18/40 , G06T7/13 , G06T7/143 , G06V10/44 , G06V10/507 , G06T2207/20076 , G06T2207/20081 , G06T2207/20084
摘要： This invention provides a system and method for finding line features in an image that allows multiple lines to be efficiently and accurately identified and characterized. When lines are identified, the user can train the system to associate predetermined (e.g. text) labels with respect to such lines. These labels can be used to define neural net classifiers. The neural net operates at runtime to identify and score lines in a runtime image that are found using a line-finding process. The found lines can be displayed to the user with labels and an associated probability score map based upon the neural net results. Lines that are not labeled are generally deemed to have a low score, and are either not flagged by the interface, or identified as not relevant.
-
公开(公告)号：US11568629B2
公开(公告)日：2023-01-31
申请号：US16433602
申请日：2019-06-06
申请人： Cognex Corporation
发明人： Lei Wang , Vivek Anand , Lowell D. Jacobson , David Y. Li
摘要： This invention provides a system and method for finding patterns in images that incorporates neural net classifiers. A pattern finding tool is coupled with a classifier that can be run before or after the tool to have labeled pattern results with sub-pixel accuracy. In the case of a pattern finding tool that can detect multiple templates, its performance is improved when a neural net classifier informs the pattern finding tool to work only on a subset of the originally trained templates. Similarly, in the case of a pattern finding tool that initially detects a pattern, a neural network classifier can then determine whether it has found the correct pattern. The neural network can also reconstruct/clean-up an imaged shape, and/or to eliminate pixels less relevant to the shape of interest, therefore reducing the search time, as well significantly increasing the chance of lock on the correct shapes.
-
公开(公告)号：US20210233250A1
公开(公告)日：2021-07-29
申请号：US17127889
申请日：2020-12-18
申请人： Cognex Corporation
发明人： Lei Wang , Vivek Anand , Lowell D. Jacobson
摘要： This invention provides a system and method for finding line features in an image that allows multiple lines to be efficiently and accurately identified and characterized. When lines are identified, the user can train the system to associate predetermined (e.g. text) labels with respect to such lines. These labels can be used to define neural net classifiers. The neural net operates at runtime to identify and score lines in a runtime image that are found using a line-finding process. The found lines can be displayed to the user with labels and an associated probability score map based upon the neural net results. Lines that are not labeled are generally deemed to have a low score, and are either not flagged by the interface, or identified as not relevant.
-
7.发明授权公开(公告)号：US10477154B2
公开(公告)日：2019-11-12
申请号：US13788973
申请日：2013-03-07
申请人： Cognex Corporation
发明人： David Y. Li , Lei Wang
IPC分类号： H04N7/00 , H04N7/18 , B25J9/16 , G05B19/402
摘要： This invention provides a system and method for aligning a first work piece with an underlying second work piece in the presence of occlusion by the first work piece of critical alignment features of the second work piece. The vision system, which guides the motion of a manipulator holding the first work piece and a motion stage holding the second work piece, learns secondary alignment features at least one of the first and second work pieces. Using these secondary features, the vision system determines alignment between the work pieces and guides the manipulator and the motion stage to achieve alignment as the first work piece engages the second work piece. The secondary features are used to define a course alignment. Deterministic movements of the manipulator and/or motion stage are used to learn the relationship between the secondary and primary features. Secondary features are used to direct alignment.
-
8.发明申请公开(公告)号：US20140267681A1
公开(公告)日：2014-09-18
申请号：US13835759
申请日：2013-03-15
申请人： COGNEX CORPORATION
CPC分类号： G06T7/80 , G06T2207/30208 , H04N17/002
摘要： Described are methods, systems, and apparatus, including computer program products for calibrating machine vision systems. A system includes: one or more cameras; a motion rendering device; and a calibration module. The calibration module is configured to acquire, from a first camera of the one or more cameras, a plurality of images of a calibration target comprising a calibration pattern that provides a plurality of calibration features; extract calibration features of the plurality of calibration features from the plurality of images, wherein physical positions of the plurality of calibration features are in a calibration target length unit associated with the calibration target; determine a ratio between the calibration target length unit and a motion rendering device length unit associated with the motion rendering device; and provide a first calibration for the first camera based on the ratio.
摘要翻译： 描述了方法，系统和装置，包括用于校准机器视觉系统的计算机程序产品。 系统包括：一个或多个相机; 运动渲染装置; 和校准模块。 校准模块被配置为从一个或多个相机的第一相机获取包括提供多个校准特征的校准图案的校准目标的多个图像; 从所述多个图像提取所述多个校准特征的校准特征，其中所述多个校准特征的物理位置处于与所述校准目标相关联的校准目标长度单位中; 确定校准目标长度单元与与运动呈现设备相关联的运动渲染设备长度单元之间的比率; 并且基于该比率为第一相机提供第一校准。
-
公开(公告)号：US20240078801A1
公开(公告)日：2024-03-07
申请号：US18220182
申请日：2023-07-10
申请人： Cognex Corporation
发明人： Lei Wang , Vivek Anand , Lowell D. Jacobson
IPC分类号： G06V10/82 , G06F18/214 , G06F18/2415 , G06F18/40 , G06T7/13 , G06T7/143 , G06V10/44 , G06V10/50
CPC分类号： G06V10/82 , G06F18/2148 , G06F18/2415 , G06F18/40 , G06T7/13 , G06T7/143 , G06V10/44 , G06V10/507 , G06T2207/20076 , G06T2207/20081 , G06T2207/20084
摘要： This invention provides a system and method for finding line features in an image that allows multiple lines to be efficiently and accurately identified and characterized. When lines are identified, the user can train the system to associate predetermined (e.g. text) labels with respect to such lines. These labels can be used to define neural net classifiers. The neural net operates at runtime to identify and score lines in a runtime image that are found using a line-finding process. The found lines can be displayed to the user with labels and an associated probability score map based upon the neural net results. Lines that are not labeled are generally deemed to have a low score, and are either not flagged by the interface, or identified as not relevant.
-
公开(公告)号：US10753726B2
公开(公告)日：2020-08-25
申请号：US15934766
申请日：2018-03-23
申请人： Cognex Corporation
发明人： David Y. Li , Li Sun , Lowell D. Jacobson , Lei Wang
摘要： This invention provides a system and method for selecting the correct profile from a range of peaks generated by analyzing a surface with multiple exposure levels applied at discrete intervals. The cloud of peak information is resolved by comparison to a model profile into a best candidate to represent an accurate representation of the object profile. Illustratively, a displacement sensor projects a line of illumination on the surface and receives reflected light at a sensor assembly at a set exposure level. A processor varies the exposure level setting in a plurality of discrete increments, and stores an image of the reflected light for each of the increments. A determination process combines the stored images and aligns the combined images with respect to a model image. Points from the combined images are selected based upon closeness to the model image to provide a candidate profile of the surface.
-
-
-
-
-
-
-
-
-
搜索结果
19 条记录 (耗时 0.017 秒)
