Image processing methods and systems

• US 7,421,116 B2
• Filed: 03/25/2004
• Issued: 09/02/2008
• Est. Priority Date: 03/25/2004
• Status: Expired due to Fees

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Chao, Hui, Fan, Jian
• Primary Examiner(s): Couso; Jose L.
• Application Number:
  US10/809,234
• Publication Number:
  US 20050213848A1
• Time in Patent Office: 1,622 Days
• Field of Search: 382/173, 382/176, 382/180, 382/282, 382/284, 382/164, 358/1.18, 358/2.1, 348/578, 707/104.1, 715/517, 715/530
• US Class Current: 382/164
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text

Abstract

Systems and methods according to the present invention provide techniques to automatically insert an object from one image into a region of another image. The systems and methods require little or no user interaction to allow efficient re-use and updating of existing images, presentations, documents and the like. An object and a container region are identified. Feasible placement location(s) within the container region for the object, as well as an associated scale factor, are determined. If multiple feasible placement locations are identified for a particular scale factor, then one is selected based upon predetermined criteria. The object can then be inserted into the container region and the resulting composite image stored or, alternatively, parameters can be stored which enable object insertion at a subsequent processing step.

Claims

1. A computer implemented method for image processing comprising:

identifying a container region in a first image by evaluating pixels neighboring a seed pixel to determine if said pixels have a same or substantially same color value as said seed pixel; and

growing said container region by iteratively identifying pixels having said same or substantially same color value;

identifying an object in a second image;

determining a placement location for the object within said container region and a scale factor associated therewith;

inserting said object into said container region at said placement location using said scale factor to generate a composite image; and

outputting said composite image.

2. The computer implemented method of claim 1, wherein identifying said object in a second image further comprises evaluating pixels in a boundary region to determine if said pixels have a same or substantially same color value to as a boundary pixel;

and growing said boundary region by iteratively identifying pixels having said same or substantially same color value.

3. The method of claim 1, wherein determining a placement location within said container region and said scale factor associated with said object further comprises

determining a scale factor;

determining whether said object will fit into said container region at said scale factor;

if said object will fit into said container region at at least one location, selecting a placement location for said object; and

otherwise, reducing said scale factor and determining whether said object will fit into said container region at said reduced scale factor.

4. The method of claim 1, further comprising downsampling said first image prior to identifying said container region.

5. The method of claim 1, wherein selecting said placement location for said object further comprises identifying a plurality of feasible placement locations for said object within said container region at said scale factor;

and selecting one of said plurality of feasible placement locations as said placement location.

6. The method of claim 5, wherein selecting one of said plurality of feasible placement locations as said placement location further comprises determining a mean center associated with origin points of said plurality of feasible placement locations;

and selecting said mean center as an origin point of said placement location.

7. The method of claim 1, wherein inserting said object into said container region at said placement location using said scale factor further comprises determining a boundary associated with a scaled version of said object;

storing said boundary and said placement location; and

inserting said object into said container region using said stored boundary and placement location.

21. The computer implemented method of claim 2 wherein the second image includes the object and a portion which forms a background to the object and wherein the background portion of the second image and the container region of the first image both have the same or substantially same color associated with them.

22. The computer implemented method of claim 1 wherein evaluating pixels neighboring a seed pixel to determine if said pixels have a same or substantially same color value as said seed pixel further comprises determining whether a Euclidean distance between a color value of the seed pixel and a color value of the neighboring pixel is within a predetermined threshold distance.

8. A computer-readable medium comprising a software program encoded thereon which when executed by a processor causes the processor to perform a method for generating a composite image comprising:

identifying a container region in a first image by evaluating pixels neighboring a seed pixel to determine if said pixels have a same or substantially same color value as said seed pixel and growing said container region by iteratively identifying pixels having said same or substantially same color value;

identifying an object in a second image;

determining a placement location for the object within said container region and a scale factor associated therewith;

inserting said object into said container region at said placement location using said scale factor to generate a composite image; and

outputting said composite image.

9. The computer-readable medium of claim 8, wherein identifying said object in a second image further comprises evaluating pixels in a boundary region to determine if said pixels have a same or substantially same color value to as a boundary pixel;

and growing said boundary region by iteratively identifying pixels having said same or substantially same color value.

10. The computer-readable medium of claim 8, wherein determining a placement location within said container region and said scale factor associated with said object further comprises

determining a scale factor;

determining whether said object will fit into said container region at said scale factor;

if said object will fit into said container region at at least one location, selecting a placement location for said object; and

otherwise, reducing said scale factor and determining whether said object will fit into said container region at said reduced scale factor.

11. The computer-readable medium of claim 8, further comprising downsampling said first image prior to identifying said container region.

12. The computer-readable medium of claim 8, wherein selecting said placement location for said object further comprises identifying a plurality of feasible placement locations for said object within said container region at said scale factor;

and selecting one of said plurality of feasible placement locations as said placement location.

13. The computer-readable medium of claim 12, wherein selecting one of said plurality of feasible placement locations as said placement location further comprises determining a mean center associated with origin points of said plurality of feasible placement locations;

and selecting said mean center as an origin point of said placement location.

14. The computer-readable medium of claim 8, wherein inserting said object into said container region at said placement location using said scale factor further comprises determining a boundary associated with a scaled version of said object;

storing said boundary and said placement location; and

inserting said object into said container region using said stored boundary and placement location.

15. An image processing system comprising:

a processor for inserting an object into a container region by;

identifying said container region by evaluating pixels neighboring a seed pixel to determine if said pixels have a same or substantially same color value as said seed pixel;

growing said container region by iteratively identifying pixels having said same or substantially same color value;

segmenting said object and said container region;

determining a placement location within said container region for said object and a scale factor associated therewith; and

inserting said object into said container region at said placement location using said scale factor to generate a composite image; and

an output device for outputting said composite image.

16. The image processing system of claim 15, wherein said processor identifies said object by evaluating pixels in a boundary region to determine if said pixels have a same or substantially same color value to as a boundary pixel;

and growing said boundary region by iteratively identifying pixels having said same or substantially same color value.

17. The image processing system of claim 15, wherein said processor determines a placement location within said container region and said scale factor associated with said object by:

determining a scale factor;

determining whether said object will fit into said container region at said scale factor;

if said object will fit into said container region at at least one location, selecting a placement location for said object; and

otherwise, reducing said scale factor and determining whether said object will fit into said container region at said reduced scale factor.

18. The image processing system of claim 15, wherein said processor identifies a plurality of feasible placement locations for said object within said container region at said scale factor;

and selects one of said plurality of feasible placement locations as said placement location.

19. The image processing system of claim 18, wherein said processor determines a mean center associated with origin points of said plurality of feasible placement locations and selects said mean center as an origin point of said placement location.

20. The image processing system of claim 15, further comprising:

a memory device for storing a boundary associated with a scaled version of said object;

wherein said processor inserts said object into said container region using said stored boundary and placement location.

23. A computer implemented method for image processing comprising:

identifying a container region in a first image;

identifying an object in a second image to be inserted into the container region by evaluating pixels in a boundary region to determine if said pixels have a same or substantially same color value to as a boundary pixel; and

growing said boundary region by iteratively identifying pixels having said same or substantially same color value;

inserting said object into said container region to generate a composite image; and

outputting said composite image.

24. The computer implemented method of claim 23 wherein said boundary region surrounds the object and said boundary region starts growing from pixels forming a boundary of the second image and grows inward toward the object in the second image.

25. A computer-readable medium comprising a software program encoded thereon which when executed by a processor causes the processor to perform a method of generating a composite image comprising:

identifying a container region in a first image;

identifying an object in a second image to be inserted into the container region by evaluating pixels in a boundary region to determine if said pixels have a same or substantially same color value to as a boundary pixel; and

growing said boundary region by iteratively identifying pixels having said same or substantially same color value;

inserting said object into said container region to generate a composite image; and

outputting said composite image.

26. The computer-readable medium of claim 25 wherein said boundary region surrounds the object, and said boundary region starts growing from pixels forming a boundary of the second image and grows inward toward the object in the second image.