INFORMATION SEARCH AND RETRIEVAL SYSTEM

• US 20110106845A1
• Filed: 12/21/2010
• Published: 05/05/2011
• Est. Priority Date: 10/27/1997
• Status: Abandoned Application

• Current Assignee: Massachusetts Institute of Technology
• Original Assignee: Massachusetts Institute of Technology
• Inventors: Sinha, Pawan, Lipson, Pamela R.
• Application Number:
  US12/975,192
• Publication Number:
  US 20110106845A1
• Time in Patent Office: Days
• US Class Current: 707/769
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 2207/30141 Printed circuit board [PCB]
• CPC Class Codes: G06T 2207/30148 Semiconductor; IC; Wafer
• CPC Class Codes: G06T 2207/30152 Solder
• CPC Class Codes: G06T 7/0006 using a design-rule based approach
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06T 7/97 Determining parameters from multiple pictures depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85
• CPC Class Codes: G06V 10/754 involving a deformation of the sample pattern or of the reference pattern; Elastic matching
• CPC Class Codes: G06V 2201/06 Recognition of objects for industrial automation
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

Method and systems for search and retrieval of images with an image processing system is disclosed. With an input interface, selection of a plurality of images to use in a search query is accepted. The plurality of images of the search query are processed with the image processing system. A subset of the plurality of target images that are similar to the plurality of images is determined. With an output interface, the subset of the plurality of target images as a result from the search query is output.

Claims

1. An image processing engine for search and retrieval of images, the image processing engine comprising:

an output interface;

an input interface, wherein the input interface accepts selection of a plurality of images to use in a search query;

a plurality of target images; and

an image processing system, wherein;

the image processing system, wherein;

the image processing system uses the plurality of images in the search query, and

the image processing system determines a subset of the plurality of target images that are similar to the plurality of images.

2. The image processing engine for search and retrieval of images as recited in claim 1, wherein the plurality of images are of bad connection points for a circuit card.

3. The image processing engine for search and retrieval of images as recited in claim 1, wherein the image processing system combines the plurality of images into a composite image used in the search query.

4. The image processing engine for search and retrieval of images as recited in claim 1, wherein the input interface receives selection of a region to be emphasized in the search query.

5. The image processing engine for search and retrieval of images as recited in claim 1, wherein the plurality of images include at least one positive example image that typifies what should be found with the search query.

6. The image processing engine for search and retrieval of images as recited in claim 1, wherein the plurality of images include at least one negative example image that typifies what should not be found with the search query.

7. The image processing engine for search and retrieval of images as recited in claim 1, wherein the image processing system learns over time parameters for best determining the subset.

8. The image processing engine for search and retrieval of images as recited in claim 1, wherein the image processing system scales at least a portion of one of the plurality of images and the plurality of target images to a similar scale.

9. A method for search and retrieval of images with an image processing system, the method comprising:

accepting, with an input interface, selection of a plurality of images to use in a search query;

processing the plurality of images of the search query with the image processing system;

determining a subset of the plurality of target images that are similar to the plurality of images; and

outputting, with an output interface, the subset of the plurality of target images as a result from the search query.

10. The method for search and retrieval of images with the image processing system as recited in claim 9, further comprising combining, using the image processing system, the plurality of images into a composite image used in the search query.

11. The method for search and retrieval of images with the image processing system as recited in claim 9, further comprising receiving, with the input interface, selection of a region to be emphasized in the search query.

12. The method for search and retrieval of images with the image processing system as recited in claim 9, wherein the plurality of images include at least one positive example image that typifies what should be found with the search query.

13. The method for search and retrieval of images with the image processing system as recited in claim 9, wherein the plurality of images include at least one negative example image that typifies what should not be found with the search query.

14. The method for search and retrieval of images with the image processing system as recited in claim 9, further comprising determining, over time with the image processing system, parameters for best determining the subset.

15. The method for search and retrieval of images with the image processing system as recited in claim 9, further comprising scaling, with the image processing system, at least a portion of one of the plurality of images and the plurality of target images to a similar scale.

16. A storage medium with computer-readable instructions for execution on a processor, comprising code for:

accepting, with an input interface, selection of a plurality of images to use in a search query;

processing the plurality of images of the search query with the image processing system;

determining a subset of the plurality of target images that are similar to the plurality of images; and

outputting, with an output interface, the subset of the plurality of target images as a result from the search query.

17. The storage medium with computer-readable instructions for execution on the processor as recited in claim 16, further comprising code for combining, using the image processing system, the plurality of images into a composite image used in the search query.

18. The storage medium with computer-readable instructions for execution on the processor as recited in claim 16, further comprising code for receiving, with the input interface, selection of a region to be emphasized in the search query.

19. The storage medium with computer-readable instructions for execution on the processor as recited in claim 16, wherein the plurality of images include at least one positive example image that typifies what should be found with the search query.

20. The storage medium with computer-readable instructions for execution on the processor as recited in claim 16, wherein the plurality of images include at least one negative example image that typifies what should not be found with the search query.

21. The storage medium with computer-readable instructions for execution on the processor as recited in claim 16, further comprising code for determining, over time with the image processing system, parameters for best determining the subset.

22. The storage medium with computer-readable instructions for execution on the processor as recited in claim 16, further comprising code for scaling, with the image processing system, at least a portion of one of the plurality of images and the plurality of target images to a similar scale.

23-72. -72. (canceled)