Non-linear image scaling with seam energy

• US 8,218,900 B1
• Filed: 07/31/2008
• Issued: 07/10/2012
• Est. Priority Date: 07/31/2008
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Avidan, Shmuel, Chien, Jen-Chan, Intwala, Chintan
• Primary Examiner(s): Koziol, Stephen R
• Application Number:
  US12/183,974
• Time in Patent Office: 1,440 Days
• Field of Search: 382/100, 382/284, 382/293, 382/295, 382/300, 345/629
• US Class Current: 382/284
• CPC Class Codes: G06T 3/04 Context-preserving transformations, e.g. by using an importance map panospheric to cylindrical image transformations G06T3/12

Abstract

A system and method for expansion and reduction of images uses a hybrid resizing technique that combines seam carving and image scaling techniques to reduce or expand an image. Seam carving techniques may be used to identify one or more low-cost seams of an input image, and these low-cost seams may be scaled up or down to expand or reduce the overall input image and produce a resized image. A different scaling factor may be applied to different ones of the low-cost seams, dependent on the average or total energy value of each of the seams. The scaling factor applied to each seam may be dependent on the number of low-cost seams identified for scaling, which may be configurable by a user. A configurable look-up table may map seam costs to scaling factors, and may be accessed to determine a respective scaling factor to be applied to each identified seam.

Claims

1. A system, comprising:

one or more processors; and

a memory coupled to the one or more processors and storing program instructions executable by the one or more processors to implement;

accessing data representing an image;

determining a respective energy value for each pixel of the image dependent on a value associated with each pixel;

identifying a seam of the image having a lowest cost, wherein the cost of the seam is dependent on the respective energy values of pixels of the seam; and

performing a resizing operation on the image along the identified seam to produce a resized version of the image, wherein said performing comprises applying an image scaling technique to the identified seam.

2. The system of claim 1, wherein the program instructions are further executable to implement repeating said identifying and said performing for a next lowest cost seam until the resized version of the image meets a specified target size or a specified target aspect ratio.

3. The system of claim 2, wherein said performing comprises applying a respective scaling factor to the scaling of each of at least two identified seams.

4. The system of claim 3, wherein the program instructions are further executable to implement:

determining a number of seams for which to repeat said identifying and said performing; and

determining the respective scaling factor for each identified seam dependent on the determined number of seams.

5. The system of claim 4, wherein said determining a number of seams is dependent on user input.

6. The system of claim 3, wherein the program instructions are further executable to implement modifying a respective scaling factor dependent on user input.

7. The system of claim 3, wherein the respective scaling factor of the lowest cost seam is greater than the respective scaling factor of the next lowest cost seam.

8. The system of claim 3, wherein the program instructions are further executable to implement determining a respective scaling factor for each seam dependent on a look-up table configured to map respective scaling factors to seam costs or seam cost ranges.

9. The system of claim 1, wherein the cost of each seam is dependent on one or more of:

a sum of the respective energy values of all pixels of the seam, an average of the respective energy values of all pixels of the seam, a weighted average of the respective energy values of all pixels of the seam, or a maximum value of the respective energy values of all pixels of the seam.

10. The system of claim 1, wherein said identifying one or more seams comprises identifying a shortest path across the image.

11. The system of claim 1, wherein said identifying one or more seams comprises applying a dynamic programming technique.

12. The system of claim 1, wherein the program instructions are further executable to implement re-sampling the resized version of the image to generate an output image.

13. The system of claim 1, wherein the value associated with each pixel represents one or more of:

an absolute color value, an absolute intensity value, a difference in color values, a difference in intensity values, a derivative of two or more pixel values, an average of two or more pixel values, a maximum of two or more pixel values, or a minimum of two or more pixel values.

14. The system of claim 1, wherein the one or more processors comprise at least one of:

a general-purpose central processing unit (CPU), or a graphics processing unit (GPU).

15. A non-transitory computer-readable storage medium, comprising program instructions computer-executable to implement:

accessing data representing an image;

determining a respective energy value for each pixel of the image dependent on a value associated with each pixel;

identifying a seam of the image having a lowest cost, wherein the cost of the seam is dependent on the respective energy values of pixels of the seam; and

performing a resizing operation on the image along the identified seam to produce a resized version of the image, wherein said performing comprises applying an image scaling technique to the identified seam.

16. The storage medium of claim 15, wherein the program instructions are further executable to implement repeating said identifying and said performing for a next lowest cost seam until the resized version of the image meets a specified target size or a specified target aspect ratio.

17. The storage medium of claim 16, wherein said performing comprises applying a respective scaling factor to the scaling of each of at least two identified seams.

18. The storage medium of claim 17, wherein the program instructions are further executable to implement:

determining a number of seams for which to repeat said identifying and said performing; and

determining the respective scaling factor for each identified seam dependent on the determined number of seams.

19. The storage medium of claim 18, wherein said determining a number of seams is dependent on user input.

20. The storage medium of claim 17, wherein the program instructions are further executable to implement modifying a respective scaling factor dependent on user input.

21. The storage medium of claim 17, wherein the respective scaling factor of the lowest cost seam is greater than the respective scaling factor of the next lowest cost seam.

22. The storage medium of claim 17, wherein the program instructions are further executable to implement determining a respective scaling factor for each seam dependent on a look-up table configured to map respective scaling factors to seam costs or seam cost ranges.

23. The storage medium of claim 15, wherein the cost of each seam is dependent on one or more of:

a sum of the respective energy values of all pixels of the seam, an average of the respective energy values of all pixels of the seam, a weighted average of the respective energy values of all pixels of the seam, or a maximum value of the respective energy values of all pixels of the seam.

24. The storage medium of claim 15, wherein said identifying one or more seams comprises one or more of:

identifying a shortest path across the image, or applying a dynamic programming technique.

25. The storage medium of claim 15, wherein the program instructions are further executable to implement re-sampling the resized version of the image to generate an output image.

26. The storage medium of claim 15, wherein the value associated with each pixel represents one or more of:

an absolute color value, an absolute intensity value, a difference in color values, a difference in intensity values, a derivative of two or more pixel values, an average of two or more pixel values, a maximum of two or more pixel values, or a minimum of two or more pixel values.

27. A computer-implemented method, comprising:

accessing data representing an image;

determining a respective energy value for each pixel of the image dependent on a value associated with each pixel;

identifying a seam of the image having a lowest cost, wherein the cost of the seam is dependent on the respective energy values of pixels of the seam; and

performing a resizing operation on the image along the identified seam to produce a resized version of the image, wherein said performing comprises applying an image scaling technique to the identified seam.

28. The method of claim 27, further comprising repeating said identifying and said performing for a next lowest cost seam until the resized version of the image meets a specified target size or a specified target aspect ratio.

29. The method of claim 28, wherein said performing comprises applying a respective scaling factor to the scaling of each of at least two identified seams.

30. The method of claim 29, further comprising:

determining a number of seams for which to repeat said identifying and said performing; and

determining the respective scaling factor for each identified seam dependent on the determined number of seams.

31. The method of claim 29, further comprising modifying a respective scaling factor dependent on user input.

32. The method of claim 29, wherein the respective scaling factor of the lowest cost seam is greater than the respective scaling factor of the next lowest cost seam.

33. The method of claim 29, further comprising determining a respective scaling factor for each seam dependent on a look-up table configured to map respective scaling factors to seam costs or seam cost ranges.

34. The method of claim 27, wherein the cost of each seam is dependent on one or more of:

a sum of the respective energy values of all pixels of the seam, an average of the respective energy values of all pixels of the seam, a weighted average of the respective energy values of all pixels of the seam, or a maximum value of the respective energy values of all pixels of the seam.

35. The method of claim 27, wherein said identifying one or more seams comprises one or more of:

identifying a shortest path across the image, or applying a dynamic programming technique.

36. The method of claim 27, further comprising re-sampling the resized version of the image to generate an output image.

37. The method of claim 27, wherein the value associated with each pixel represents one or more of:

an absolute color value, an absolute intensity value, a difference in color values, a difference in intensity values, a derivative of two or more pixel values, an average of two or more pixel values, a maximum of two or more pixel values, or a minimum of two or more pixel values.