Method and apparatus for configuring and testing a machine vision detector
First Claim
1. A method for configuring an image analysis device to inspect objects comprising:
- continuously moving a sequence of objects being manufactured in a production environment relative to a field of view of the image analysis device;
capturing a sequence of images of the field of view, such that the sequence of images includes a plurality of images of each of a plurality of objects from the sequence of objects being manufactured in the production environment;
displaying a portion of the sequence of images on a graphical user interface, the portion displayed chosen responsive to scrolling commands, the scrolling commands advancing the portion forward and backward in the sequence of images;
choosing, during a training phase, a first training image from the displayed portion of the sequence of images of a training object, the first training image being selected depending upon particular features recognized on the training object during the training phase;
configuring the image analysis device by creating, using the first training image chosen during the training phase, at least one vision tool to inspect objects similar in appearance to the training object of the first training image, the at least one vision tool being represented by a graphical image on the graphical user interface; and
performing an image analysis operation on the first training image to detect a feature on the training object of the training image, by computing a logic value to determine whether the feature is located in the field of view for each of the plurality of images such that the feature is determined to be located in the field of view for at least one image of the plurality of images when the logic value for the feature located in the field of view for the at least one image is greater than a threshold value.
3 Assignments
0 Petitions
Accused Products
Abstract
Disclosed are systems and methods for configuring a vision detector, wherein a training image is obtained from a production line operating in continuous motion so as to provide conditions substantially identical to those that will apply during actual manufacturing and inspection of objects. A training image can be obtained without any need for a trigger signal, whether or not the vision detector might use such a signal for inspecting the objects. Further disclosed are systems and methods for testing a vision detector by selecting, storing, and displaying a limited number of images from a production run, where those images correspond to objects likely to represent incorrect decisions.
-
Citations
29 Claims
-
1. A method for configuring an image analysis device to inspect objects comprising:
-
continuously moving a sequence of objects being manufactured in a production environment relative to a field of view of the image analysis device; capturing a sequence of images of the field of view, such that the sequence of images includes a plurality of images of each of a plurality of objects from the sequence of objects being manufactured in the production environment; displaying a portion of the sequence of images on a graphical user interface, the portion displayed chosen responsive to scrolling commands, the scrolling commands advancing the portion forward and backward in the sequence of images; choosing, during a training phase, a first training image from the displayed portion of the sequence of images of a training object, the first training image being selected depending upon particular features recognized on the training object during the training phase; configuring the image analysis device by creating, using the first training image chosen during the training phase, at least one vision tool to inspect objects similar in appearance to the training object of the first training image, the at least one vision tool being represented by a graphical image on the graphical user interface; and performing an image analysis operation on the first training image to detect a feature on the training object of the training image, by computing a logic value to determine whether the feature is located in the field of view for each of the plurality of images such that the feature is determined to be located in the field of view for at least one image of the plurality of images when the logic value for the feature located in the field of view for the at least one image is greater than a threshold value. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. An apparatus comprising:
-
an image analysis device that captures images of a continuously moving sequence of objects being manufactured in a production environment to provide a sequence of images, the sequence of objects having a motion relative to the image analysis device, the image analysis device having a frame rate such that the sequence of images includes a plurality of images of each of a plurality of objects from the sequence of objects being manufactured in the production environment; a human-machine interface configured to display a portion of the sequence of images; a selection means for choosing, during a training phase, a training image from the sequence of images of a training object, the first training image being selected depending upon particular features recognized on the training object during the training phase; a configuring means for configuring the image analysis device, using the training image selected during the training phase, at least one vision tool to inspect objects similar in appearance to the training object of the first training image, the at least one vision tool being represented by a graphical image on the graphical user interface; and wherein the image analysis device performs an image analysis operation on the first training image to detect a feature on the training object of the training image, by computing a logic value to determine whether the feature is located in the field of view for each of the plurality of images such that the feature is determined to be located in the field of view for at least one image of the plurality of images when the logic value for the feature located in the field of view for the at least one image is greater than a threshold value. - View Dependent Claims (11, 12, 13, 14)
-
-
15. A method for configuring an image analysis device to inspect objects comprising the steps of:
-
capturing a sequence of images of a field of view of the image analysis device, the sequence of images including a plurality of images of each of a plurality of objects, the plurality of objects continuously moving relative to the field of view; displaying a portion of the sequence of images on a graphical user interface; defining, during a training phase, a first training image based upon a selection of an image from the displayed portion of the sequence of images of a training object, the first training image being selected depending upon particular features recognized on the training object during the training phase; configuring the image analysis device by creating, using the first training image chosen during the training phase, at least one vision tool to inspect objects similar in appearance to the training object of the first training image, the at least one vision tool comprising one or more of a locator, a contrast detector, a brightness detector, and an edge detector; and performing an image analysis operation on the first training image to detect a feature on the training object of the training image, by computing a logic value to determine whether the feature is located in the field of view for each of the plurality of images such that the feature is determined to be located in the field of view for at least one image of the plurality of images when the logic value for the feature located in the field of view for the at least one image is greater than a threshold value. - View Dependent Claims (16, 17, 18, 19, 20, 21, 22, 23, 24)
-
-
25. An apparatus comprising:
-
an image analysis device that captures images of a continuously moving sequence of objects to provide a sequence of images, the sequence of objects having a motion relative to the image analysis device, the image analysis device having a frame rate such that the sequence of images includes a plurality of images of each of a plurality of objects from the sequence of objects; a human-machine interface configured to display a portion of the sequence of images; an image view window for enabling selection of a training image during a training phase from the sequence of images of a training object, the first training image being selected depending upon particular features recognized on the training object during the training phase; at least one vision tool created, using the first training image, to inspect objects similar in appearance to the training object of the first training image, and to configure the image analysis device, the at least one vision tool comprising one or more of a locator, a contrast detector, a brightness detector, and an edge detector; and wherein the image analysis device performs an image analysis operation on the first training image to detect a feature on the training object of the training image, by computing a logic value to determine whether the feature is located in the field of view for each of the plurality of images such that the feature is determined to be located in the field of view for at least one image of the plurality of images when the logic value for the feature located in the field of view for the at least one image is greater than a threshold value. - View Dependent Claims (26, 27, 28, 29)
-
Specification