System and method for machine vision analysis of an object using a reduced number of cameras

• US 6,493,079 B1
• Filed: 09/07/2000
• Issued: 12/10/2002
• Est. Priority Date: 09/07/2000
• Status: Expired due to Term

• Current Assignee: National Instruments Corporation (Emerson Electric Company)
• Original Assignee: National Instruments Corporation (Emerson Electric Company)
• Inventors: Piacentini, Ignazio
• Primary Examiner(s): STAFIRA, MICHAEL PATRICK
• Application Number:
  US09/656,571
• Time in Patent Office: 824 Days
• Field of Search: 356/237--23, 356/240.1, 356/625, 356/627, 356/628, 356/634, 356/635, 356/638-640, 382/141, 382/154
• US Class Current: 356/240.1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06V 10/147 Details of sensors, e.g. sensor lenses fingerprint or palmprint sensors G06V40/13; vascular sensors G06V40/145; eye sensors G06V40/19

Abstract

A system and method for analyzing an object using a reduced number of cameras and/or a reduced number of acquired images. The system and method may be utilized in a machine vision application, e.g., in order to inspect manufactured objects. The method may operate to acquire an image, or a plurality of images, of the object. In order to reduce the number of images that need to be acquired, at least one of the acquired images includes visual information for two or more sides of the object. Such an image may be acquired by a camera positioned in any of various ways such that the camera can capture visual information for multiple sides of the object. The acquired images of the object may then be received by computer systems connected to the cameras and analyzed using image processing software. For each image that includes visual information for multiple sides of the object, analyzing the image may comprise determining regions of interest within the image, wherein each region of interest corresponds to one side of the object. Each of these regions of interest may then be analyzed separately. In a machine vision manufacturing application, the results of the image analyses may be used to determine whether the object meets desired production standards. The images or ROIs may be analyzed using any of various techniques or algorithms designed to detect any of various characteristics or defects of the object.

Claims

1. A method for analyzing an object having a plurality of sides, the method comprising:

acquiring a first image of the object, wherein the first image includes visual information for at least two sides of the object;

determining a plurality of regions within the first image, wherein each region corresponds to one side of the object; and

analyzing each of the regions separately using image processing software;

wherein said analyzing each of the regions comprises analyzing the visual information for the at least two sides of the object, wherein said analyzing each of the regions analyzes the at least two sides of the object.

2. The method of claim 1, wherein the object is a manufactured object, wherein said acquiring and analyzing are performed for a machine vision application to inspect a plurality of manufactured objects, the method further comprising:

for each manufactured object;

determining whether the manufactured object meets desired production standards, based on said analyzing;

rejecting the manufactured object if the manufactured object does not meet the desired production standards.

3. The method of claim 1,

wherein the first image includes visual information for at least three sides of the object.

4. The method of claim 1,

wherein said analyzing comprises analyzing the visual information to determine one or more physical characteristics of at least one of the sides of the object.

5. The method of claim 1,

wherein said analyzing comprises analyzing the visual information of the image for one or more of:

a physical defect on a side of the object;

a component located correctly on the object;

a correct label on the object;

a correct marking on the object;

correct color information on the object.

6. The method of claim 1,

wherein said analyzing comprises performing one or more of the following:

a pattern matching algorithm;

a color matching algorithm;

a color and pattern matching algorithm.

7. The method of claim 1, further comprising:

acquiring a plurality of images of the object, wherein each image includes visual information for at least two sides of the object, wherein the first image is one of the plurality of images;

analyzing each of the plurality of images using image processing software.

8. The method of claim 1,

wherein the object is a rectangular prism having six sides;

wherein the first image includes visual information for three sides of the object.

9. The method of claim 8,

wherein a first corner of the object is defined by an intersection of each of three planes including the three sides for which visual information is included in the first image;

wherein a second corner of the object is defined by an intersection of each of three planes including the three sides for which visual information is not included in the first image;

wherein the first image is acquired by a camera positioned along a diagonal axis connecting the first corner and the second corner.

10. A machine vision system for inspecting a plurality of objects having multiple sides, the system comprising:

a first camera operable to acquire images of the objects, wherein for each object, the first camera is operable to acquire a first image having visual information for two or more sides of the object;

a computer system connected to the first camera, wherein the computer system includes a processor and memory, wherein the computer system is operable to receive acquired first images from the first camera;

wherein the memory of the computer system stores image processing software;

wherein the processor of the computer system is operable to execute the image processing software in order to analyze the first images received from the cameras;

wherein, in analyzing the first image, the processor is operable to;

determine a plurality of regions within the first image, wherein each region corresponds to one side of the object; and

execute the image processing software in order to analyze each of the regions separately, wherein said analyzing each of the regions analyzes the visual information for the two or more sides of the object;

wherein said analyzing the images inspects the plurality of objects.

11. The system of claim 10,

wherein the first image acquired for each object by the first camera includes visual information for at least three sides of the object.

12. The system of claim 10,

wherein said analyzing the first image comprises analyzing the visual information to determine one or more physical characteristics of at least one of the sides of the object.

13. The system of claim 10,

wherein said analyzing the first image comprises analyzing the visual information of the image for one or more of:

a physical defect on a side of the object;

a component located correctly on the object;

a correct label on the object;

a correct marking on the object;

correct color information on the object.

14. The system of claim 10,

wherein said analyzing the first image comprises performing one or more of the following on the first image:

a pattern matching algorithm;

a color matching algorithm;

a color and pattern matching algorithm.

15. The system of claim 10,

wherein each image acquired by the cameras includes visual information for at least two sides of the object.

16. A machine vision system for inspecting a plurality of objects having multiple sides, the system comprising:

a plurality of cameras operable to acquire images of the objects, wherein for each object, a first camera is operable to acquire a first image having visual information for two or more sides of the object;

a plurality of computer systems, wherein each computer system is connected to one of the cameras, wherein each computer system includes a processor and memory, wherein each computer system is operable to receive acquired images from the camera connected to the computer system;

wherein the memory of each computer system stores image processing software;

wherein the processor of each computer system is operable to execute the image processing software in order to analyze the images received from the camera connected to the computer system;

wherein said analyzing the images comprises the computer system connected to the first camera analyzing the first image acquired for each object;

wherein in analyzing the first image acquired for each object, the computer system connected to the first camera is operable to;

determine a plurality of regions within the first image, wherein each region corresponds to one side of the object; and

analyze each of the regions separately, wherein said analyzing each of the regions analyzes the visual information for the two or more sides of the object;

wherein said analyzing the images inspects the plurality of objects.

17. A memory medium for analyzing an object having a plurality of sides, the memory medium comprising program instructions executable to:

receive a first image of the object, wherein the first image includes visual information for at least two sides of the object; and

analyze the first image, wherein said analyzing the first image comprises;

determining a plurality of regions within the first image, wherein each region corresponds to one side of the object; and

analyzing each of the regions separately;

wherein said analyzing each of the regions analyzes the visual information for the at least two sides of the object, wherein said analyzing each of the regions analyzes the at least two sides of the object.

18. The memory medium of claim 17,

wherein the first image includes visual information for at least three sides of the object.

19. The memory medium of claim 17,

wherein said analyzing the first image comprises analyzing the visual information to determine one or more physical characteristics of at least one of the sides of the object.