Method and apparatus for human interface to a machine vision system
View Patent ↗An apparatus and method are disclosed for setting up a vision system having a camera and a vision processor cooperative with the camera. The apparatus includes a gesture recognizer, a key recognizer, a breakout box having at least two signaling elements, and a setup control unit that is cooperative with the gesture recognizer, the key recognizer, and the breakout box. The combination of using a key and a gesture set as herein described is substantially superior, as compared with known user interfaces for setting up a vision system that has been previously been engineered, in terms of low-cost, convenience, ease-of-use, simplicity, and speed.
1. A method for training a vision system, the method comprising:
instructing the vision system to enter a region of interest training mode by showing a region of interest training mode key to the vision system, the vision system entering the region of interest training mode based on the showing the region of interest training mode key;
indicating a contour of a region of interest to the vision system by showing the region of interest to the vision system using a training key, the training key graphically indicating the contour of the region of interest; and
instructing the vision system to enter a run mode by showing a run mode key to the vision system, the vision system entering the run mode based on the showing the run mode key.
2. The method of claim 1 , wherein the training key is manually drawn.
3. The method of claim 1 , wherein the training key is selected from a set of training keys.
4. The method of claim 3 , wherein the set of training keys is included in a users manual.
5. The method of claim 1 further including:
creating an inspection routine based on the contour of the region of interest.
6. The method of claim 1 further including:
acquiring an image of the object during the run mode; and
analyzing at least a portion of the image of the object that is positioned within the region of interest.
7. The method of claim 1 , wherein the region of interest is at least a portion of a schematic of an object to be imaged by the vision system.
8. The method of claim 1 , wherein the region of interest training mode key comprises a gesture made in a field of view of the vision system.
9. A system for identifying a region of interest within a field of view of a camera during a training mode, the region of interest to be used in a subsequent analysis of an image of an object placed within the field of view during a run mode, the system comprising:
a region of interest key to be viewed within the field of view of the camera, the region of interest key having at least a contour of the region of interest graphically indicated by the region of interest key;
an image of the region of interest key; and
a processor configured to analyze the image of the region of interest key so as to identify parameters of the region of interest and use the parameters of the region of interest as input for the subsequent analysis of the image of the object.
10. The apparatus of claim 9 , wherein the key is a manual drawing.
11. The apparatus of claim 9 , wherein the key is one of a set of training keys.
12. The apparatus of claim 11 , wherein the set of training keys is included in a user's manual.
13. The apparatus of claim 9 , wherein the region of interest is a region of interest of the object.
14. The apparatus of claim 9 , wherein the region of interest key to be viewed within the field of view of the camera is viewed without the object during the training mode.
15. A computer program product, tangibly embodied in a non-transitory computer readable medium, the computer program product including instructions being operable to cause a data processing apparatus to:
analyze a region of interest training mode key to place a vision system into a region of interest training mode;
calculate a region of interest from an image of a training key, the training key graphically indicating contours of the region of interest; and
analyze a subsequent image of an object without the training key using at least one parameter of the calculated region of interest.
16. The product of claim 15 , wherein the training key is a manual drawing.
17. The product of claim 15 , wherein the training key is one of a set of training keys.
18. The product of claim 17 , wherein the set of training keys is included in a user's manual.
19. The product of claim 15 wherein the region of interest training mode key includes a data symbol that instructs the data processing apparatus to regard the image in a field of view of the image system as including region of interest training information.
20. A method for training a vision system, the method comprising:
recognizing, by the vision system, a region of interest training mode key to initiate a region of interest training mode;
identifying, by the vision system, contours of a region of interest based on a region of interest key that graphically indicates the contours of the region of interest during the region of interest training mode; and
recognizing, by the vision system, a run mode key to initiate a run mode of the vision system.
21. The method of claim 20 further including:
acquiring an image of the object without the region of interest key during the run mode.
22. The method of claim 20 , wherein the region of interest is a region of interest of an object.