Automatic labeling system
Systems for automatic labeling and methods for using automatic labeling systems are disclosed. A system can include a camera, and a controller including one or more processors coupled to one or more memories. The system can acquire an image of a sample object via the camera, and identify first and second tokens depicted in the image or positioned over the image of the sample object. The system can designate a location of the first token as a target label location at which a label is to be applied to the sample object, and designate a location of the second token as an identifying information location that is identifiable to determine an orientation of the sample object.
1 . A system for automatic labeling, comprising:
a camera; and
a controller comprising one or more processors coupled to one or more memories, the controller configured to:
acquire an image of a sample object via the camera,
receive, from a graphical user interface, an input from a user defining a location of a virtual token positioned over the image of the sample object, and
store a location of the virtual token as a target label location at which a label is to be applied to the sample object.
2 . The system of claim 1 , wherein:
the target label location is stored as a location that is relative to a corner of the sample object.
3 . The system of claim 1 , wherein:
the controller is further configured to:
determine a suitability score for recognition of the sample object based on the image with and without the virtual token positioned over the image.
4 . The system of claim 1 , further comprising:
a robotic arm configured to apply labels to objects, wherein:
the controller is further configured to:
detect a location and an orientation of an object in a stream of objects, and
cause the robotic arm to apply a label to the object based on the detected location and orientation and the target label location.
5 . The system of claim 4 , wherein:
the controller is further configured to:
cause the robotic arm to move in a horizontal direction based on the detected location and orientation and the target label location, and
subsequently cause the robotic arm to move in a vertical direction based on the detected location and orientation and the target label location to apply the label to the object.
6 . The system of claim 4 , wherein:
the controller is further configured to reject a second object of the stream of objects based on an orientation of the second object.
7 . The system of claim 5 , wherein:
the controller is further configured to verify the label was correctly applied to the object.
8 . The system of claim 5 , further comprising:
a plate configured to receive printed labels from a printer, wherein:
the controller is further configured to:
cause the robotic arm to retrieve the label from the plate prior to applying the label to the object.
9 . The system of claim 2 , wherein:
the controller is further configured to:
determine one or more dimensions of the sample object, and
navigate the robotic arm to avoid a collision with the object based on the one or more dimensions of the sample object.
10 . The system of claim 9 , wherein:
the one or more dimensions comprise a height of the sample object, and
the controller is further configured to navigate the robotic arm vertically based on the height of the sample object.
11 . The system of claim 1 , wherein: the camera is a three-dimensional (3D) camera.
12 . The system of claim 1 , wherein:
the controller is further configured to generate a code for the sample object.
13 . The system of claim 1 , wherein:
the controller is further configured to:
identify a second token depicted in the image or positioned over the image of the sample object, and
designate a location of the second token as an identifying information location that is identifiable to determine an orientation of the sample object.
14 . The system of claim 13 , wherein:
the second token is a second virtual token positioned over the image via input from the user to the graphical user interface.
15 . The system of claim 13 , further comprising:
a robotic arm configured to apply labels to objects, wherein:
the controller is further configured to:
detect a location and an orientation of an object in a stream of objects based on the identifying information location, and
cause the robotic arm to apply a label to the object based on the detected location and orientation and the target label location.
16 . The system of claim 15 , wherein:
the controller is further configured to:
cause the robotic arm to move in a horizontal direction based on based on the detected location and orientation and the target label location, and
subsequently cause the robotic arm to move in a vertical direction based on the detected location and orientation and the target label location to apply the label to the object.
17 . The system of claim 15 , wherein:
the controller is further configured to reject a second object of the stream of objects based on an orientation of the second object.
18 . A method of using an automatic labeling system, the method comprising:
acquiring an image of a sample object;
receiving, from a graphical user interface, an input from a user defining a location of a virtual token positioned over the image of the sample object;
identifying the virtual token positioned over the image of the sample object; and
storing a location of the virtual token as a target label location at which a label is to be applied to the sample object.
19 . The method of claim 18 , further comprising:
identifying a second token depicted in the image or positioned over the image of the sample object; and
designating a location of the second token as an identifying information location that is identifiable to determine an orientation of the sample object.
20 . The system of claim 1 , wherein:
the target label location is stored as a location that is relative to a location of known identifying information on the sample object or a border of the sample object.
21 . The system of claim 14 , wherein:
the controller is configured to extract pixels designated by the second virtual token and utilize information in the pixels to train a model to detect an orientation of an object.
22 . The system of claim 1 , wherein:
the controller is further configured to:
generate a candidate location for a second virtual token as an identifying information location that is identifiable to determine an orientation of the sample object,
display, on the graphical user interface, the second virtual token positioned in the candidate location over the image of the sample object,
receive, from the graphical user interface, a user input from the user to adjust the location of the second virtual token,
receive, from the graphical user interface, an input from the user accepting the adjusted located of the second virtual token, and
designate the adjusted location of the second virtual token as the identifying information location that is identifiable to determine the orientation of the sample object.
23 . A system for automatic labeling, comprising:
a camera; and
a controller comprising one or more processors coupled to one or more memories, the controller configured to:
acquire an image of a sample object via the camera,
generate a candidate location for a virtual token as a target label location at which a label is to be applied to the sample object,
display, on the graphical user interface, the virtual token positioned in the candidate location over the image of the sample object,
receive, from the graphical user interface, a user input from the user to adjust the location of the virtual token,
receive, from the graphical user interface, an input from the user accepting the adjusted location of the virtual token, and
store the adjusted location of the virtual token as the target label location at which the label is to be applied to the sample object.
24 . The system of claim 23 , wherein:
the controller is further configured to, before receiving the input from the user accepting the adjusted location of the virtual token, receive, from the graphical user interface, an input from the user to adjust a size and/or a shape of the virtual token.