公开(公告)号：US20140119665A1

公开(公告)日：2014-05-01

申请号：US13797910

申请日：2013-03-12

Applicant: COGNEX CORPORATION

Inventor： Earle B. Stokes ,  Fenghua Jin ,  William M. Silver ,  Xiangyun Ye ,  Ivan A. Bachelder

IPC: G06T7/00

CPC classification number: G06K9/2063 ,  G06K7/10861 ,  G06K7/10871 ,  G06K7/1417 ,  G06K7/1443 ,  G06K9/4604 ,  G06K9/4609 ,  G06K9/4623 ,  G06T7/60

Abstract: This invention provides a system and method for finding features in images that exhibit saddle point-like structures using relatively computationally low-intensive processes, illustratively consisting of an anti-correlation process, and associated anti-correlation kernel, which operates upon a plurality of pixel neighborhoods within the image. This process enables an entire image to be quickly analyzed for any features that exhibit such saddle point-like structures by determining whether the anti-correlation kernel generates a weak or strong response in various positions within the image. The anti-correlation kernel is designed to generate a strong response regardless of the orientation of a saddle point-like structure. The anti-correlation process examines a plurality of pixel neighborhoods in the image, thereby locating any saddle point-like structures regardless of orientation, as it is angle-independent. The structures are then grouped and refined (for example in a grid) in an effort to locate and decode ID topologies within the image.

Abstract translation: 本发明提供一种用于在图像中发现特征的系统和方法，该特征使用相对计算上的低密集过程表现出鞍点状结构，其示意性地由抗相关过程和相关联的反相关核组成，该相关反相内核基于多个像素 图像内的社区。 该过程使得能够通过确定反相关内核是否在图像内的各个位置中产生弱或强响应来呈现出诸如鞍点状结构的任何特征，从而快速分析整个图像。 反相关核被设计成产生强烈的响应，而不管鞍点状结构的取向如何。 反相关处理检查图像中的多个像素邻域，从而定位任何鞍状结构，而不管方位如何，因为它是与角度无关的。 然后将结构分组和精化（例如，在网格中），以努力定位和解码图像内的ID拓扑。

公开(公告)号：US20140111656A1

公开(公告)日：2014-04-24

申请号：US13794618

申请日：2013-03-11

Applicant: COGNEX CORPORATION

Inventor： James A. Negro ,  Earle B. Stokes

IPC: H04N17/00

CPC classification number: H04N5/243 ,  G06K7/10722 ,  G06K7/1478 ,  H04N5/2353 ,  H04N5/2354 ,  H04N5/2356 ,  H04N5/35545 ,  H04N5/3559

Abstract: This invention provides a system and method for auto-regulation of parameters a vision system camera and/or associated illumination of objects imaged by the camera using a plurality of differentiated gain (multi-gain) settings on the camera's image sensor to determine the gain value producing the most-readable image. The image (having the best characteristics) acquired using multiple gain settings can be read for information as a discrete gain image and/or the camera parameters (e.g. global gain and/or global exposure time) can be uniformly set across the pixel array to the best values for acquisition of a subsequent, higher sampled image. This image is then read (e.g. decoded) for information contained within any identified features of interest (e.g. found IDs).

Abstract translation: 本发明提供了一种系统和方法，用于通过在相机的图像传感器上使用多个微分增益（多增益）设置来自动调节由相机成像的视觉系统相机和/或相关照明的参数的参数，以确定增益值 产生最可读的图像。 可以读取使用多个增益设置获取的图像（具有最佳特性），用于作为离散增益图像的信息，和/或可以将像素阵列的相机参数（例如，全局增益和/或全局曝光时间）均匀地设置为 用于获取后续较高采样图像的最佳值。 然后，读取（例如，解码）该图像，用于包含在感兴趣的所识别的特征内的信息（例如，找到的ID）。

公开(公告)号：US09946947B2

公开(公告)日：2018-04-17

申请号：US13797910

申请日：2013-03-12

Applicant: Cognex Corporation

Inventor： Earle B. Stokes ,  Fenghua Jin ,  William M. Silver ,  Xiangyun Ye ,  Ivan A. Bachelder

IPC: G06K9/50 ,  G06K9/20 ,  G06K7/14 ,  G06K9/46 ,  G06K7/10 ,  G06T7/60

CPC classification number: G06K9/2063 ,  G06K7/10861 ,  G06K7/10871 ,  G06K7/1417 ,  G06K7/1443 ,  G06K9/4604 ,  G06K9/4609 ,  G06K9/4623 ,  G06T7/60

Abstract: This invention provides a system and method for finding features in images that exhibit saddle point-like structures using relatively computationally low-intensive processes, illustratively consisting of an anti-correlation process, and associated anti-correlation kernel, which operates upon a plurality of pixel neighborhoods within the image. This process enables an entire image to be quickly analyzed for any features that exhibit such saddle point-like structures by determining whether the anti-correlation kernel generates a weak or strong response in various positions within the image. The anti-correlation kernel is designed to generate a strong response regardless of the orientation of a saddle point-like structure. The anti-correlation process examines a plurality of pixel neighborhoods in the image, thereby locating any saddle point-like structures regardless of orientation, as it is angle-independent. The structures are then grouped and refined (for example in a grid) in an effort to locate and decode ID topologies within the image.

公开(公告)号：US10110829B2

公开(公告)日：2018-10-23

申请号：US15230342

申请日：2016-08-05

Applicant: Cognex Corporation

Inventor： James A. Negro ,  Earle B. Stokes

IPC: H04N5/243 ,  G06K7/10 ,  G06K7/14

Abstract: This invention provides a system and method for auto-regulation of parameters a vision system camera and/or associated illumination of objects imaged by the camera using a plurality of differentiated gain (multi-gain) settings on the camera's image sensor to determine the gain value producing the most-readable image. The image (having the best characteristics) acquired using multiple gain settings can be read for information as a discrete gain image and/or the camera parameters (e.g. global gain and/or global exposure time) can be uniformly set across the pixel array to the best values for acquisition of a subsequent, higher sampled image. This image is then read (e.g. decoded) for information contained within any identified features of interest (e.g. found IDs).

公开(公告)号：US20170214860A1

公开(公告)日：2017-07-27

申请号：US15230342

申请日：2016-08-05

Applicant: Cognex Corporation

Inventor： James A. Negro ,  Earle B. Stokes

IPC: H04N5/243 ,  G06K7/14 ,  G06K7/10

CPC classification number: H04N5/243 ,  G06K7/10722 ,  G06K7/1478 ,  H04N5/2353 ,  H04N5/2354 ,  H04N5/2356 ,  H04N5/35545 ,  H04N5/3559

Abstract: This invention provides a system and method for auto-regulation of parameters a vision system camera and/or associated illumination of objects imaged by the camera using a plurality of differentiated gain (multi-gain) settings on the camera's image sensor to determine the gain value producing the most-readable image. The image (having the best characteristics) acquired using multiple gain settings can be read for information as a discrete gain image and/or the camera parameters (e.g. global gain and/or global exposure time) can be uniformly set across the pixel array to the best values for acquisition of a subsequent, higher sampled image. This image is then read (e.g. decoded) for information contained within any identified features of interest (e.g. found IDs).

公开(公告)号：US09413981B2

公开(公告)日：2016-08-09

申请号：US13794618

申请日：2013-03-11

Applicant: Cognex Corporation

Inventor： James A. Negro ,  Earle B. Stokes

IPC: H04N17/00 ,  H04N5/235 ,  H04N5/355 ,  H04N5/243 ,  G06K7/14

CPC classification number: H04N5/243 ,  G06K7/10722 ,  G06K7/1478 ,  H04N5/2353 ,  H04N5/2354 ,  H04N5/2356 ,  H04N5/35545 ,  H04N5/3559

Abstract: This invention provides a system and method for auto-regulation of parameters a vision system camera and/or associated illumination of objects imaged by the camera using a plurality of differentiated gain (multi-gain) settings on the camera's image sensor to determine the gain value producing the most-readable image. The image (having the best characteristics) acquired using multiple gain settings can be read for information as a discrete gain image and/or the camera parameters (e.g. global gain and/or global exposure time) can be uniformly set across the pixel array to the best values for acquisition of a subsequent, higher sampled image. This image is then read (e.g. decoded) for information contained within any identified features of interest (e.g. found IDs).

Abstract translation: 本发明提供了一种系统和方法，用于通过在相机的图像传感器上使用多个微分增益（多增益）设置来自动调节由相机成像的视觉系统相机和/或相关照明的参数的参数，以确定增益值 产生最可读的图像。 可以读取使用多个增益设置获取的图像（具有最佳特性），用于作为离散增益图像的信息，和/或可以将像素阵列的相机参数（例如，全局增益和/或全局曝光时间）均匀地设置为 用于获取后续较高采样图像的最佳值。 然后，读取（例如，解码）该图像，用于包含在感兴趣的所识别的特征内的信息（例如，找到的ID）。