Adaptive region editing tool
View Patent ↗Properties of pixels of a digital image are sampled within different subdivisions of an editing tool impression to produce different property distributions. The subdivisions may be differently-located within the tool impression. The property distributions from each region are classified to identify different edit classes within the property space, which are then used to apply an edit effect to the digital image within the tool impression. The edit classes may be represented by an edit profile in two or more dimensions (e.g., applying to one or more pixel properties).
1. A method comprising:
sampling pixels in a first predefined region of a tool impression in a digital image to determine a first distribution of a pixel property of the pixels in the first predefined region using a processing unit;
sampling pixels in a second predefined region of the tool impression to determine a second distribution of the pixel property of the pixels in the second predefined region using the processing unit; and
editing at least one pixel within the tool impression based on the first and second distributions using the processing unit.
2. The method of claim 1 wherein the editing operation comprises:
altering an editable pixel property of the at least one pixel.
3. The method of claim 1 wherein the editing operation comprises:
altering an editable pixel property of the at least one pixel, the editable pixel property being different than the sampled pixel property.
4. The method of claim 1 wherein the first and second predefined regions represent differently-located subdivisions of the tool impression.
5. The method of claim 1 wherein the editing operation comprises:
editing the at least one pixel within the tool impression according to an edit profile based on the first and second distributions of the pixel property.
6. The method of claim 5 wherein the edit profile is determined by classifying the pixel properties as a function of pixel property differences.
7. The method of claim 5 wherein the edit profile is determined by classifying the pixel properties into at least two edit classes, each edit class applying a different degree of an editing effect.
8. The method of claim 5 wherein the edit profile is determined by classifying the pixel properties into at least two edit classes, each edit class applying a different editing effect.
9. The method of claim 5 wherein the edit profile is determined by classifying the pixel properties using blind signal separation.
10. The method of claim 5 wherein the edit profile is determined by categorizing the pixel properties using a classifier.
11. The method of claim 5 wherein the edit profile is determined by classifying the pixel properties using discriminant analysis.
12. The method of claim 5 wherein the edit profile is determined by classifying the pixel properties using mixture modeling.
13. The method of claim 5 wherein the edit profile is determined by classifying the pixel properties using Bayesian statistics.
14. The method of claim 5 wherein the edit profile is determined by classifying the pixel properties using thresholds.
15. The method of claim 5 wherein the edit profile is determined by classifying the pixel properties using property variance.
16. The method of claim 5 wherein the edit profile includes overlapping edit classes, each edit class representing a different degree of editing effect.
17. The method of claim 5 wherein the edit profile includes overlapping edit classes, each edit class representing a different type of editing effect.
18. The method of claim 5 wherein the edit profile designates an edit class specifying a replacement value of an editable pixel property of the at least one pixel.
19. The method of claim 5 wherein the edit profile designates an edit class specifying a transformation of an editable pixel property of the at least one pixel.
20. The method of claim 1 wherein the editing operation comprises:
editing at least one pixel within each of the first predefined region and the second predefined region of the tool impression based on the first and second distributions of the pixel property.
21. The method of claim 1 wherein the pixel property is a composite pixel property.
22. The method of claim 1 wherein the pixel property is a multidimensional pixel property.
23. The method of claim 1 wherein the operation of sampling pixels in the first predefined region comprises:
determining a property value for each of a plurality of pixels within the first predefined region.
24. The method of claim 1 further comprising:
determining location and dimensions of the tool impression within the digital image.
25. The method of claim 1 further comprising:
identifying the pixels in the first predefined region within the tool impression of the digital image; and
identifying the pixels in the second predefined region within the tool impression of the digital image.
26. One or more non-transitory tangible computer readable media encoding a computer program for executing on a computer system a computer process, the computer process comprising:
sampling pixels in a first predefined region of a tool impression in a digital image to determine a first distribution of a pixel property of the pixels in the first predefined region;
sampling pixels in a second predefined region of the tool impression to determine a second distribution of the pixel property of the pixels in the second predefined region; and
editing at least one pixel within the tool impression based on the first and second distributions.
27. The non-transitory tangible computer readable media of claim 26 wherein the editing operation comprises:
altering an editable pixel property of the at least one pixel.
28. The non-transitory tangible computer readable media of claim 26 wherein the editing operation comprises:
altering an editable pixel property of the at least one pixel, the editable pixel property being different than the sampled pixel property.
29. The non-transitory tangible computer readable media of claim 26 wherein the first and second predefined regions represent differently-located subdivisions of the tool impression.
30. The non-transitory tangible computer readable media of claim 26 wherein the editing operation comprises:
editing the at least one pixel within the tool impression according to an edit profile based on the first and second distributions of the pixel property.
31. The non-transitory tangible computer readable media of claim 30 wherein the edit profile is determined by classifying the pixel properties as a function of pixel property differences.
32. The non-transitory tangible computer readable media of claim 30 wherein the edit profile is determined by classifying the pixel properties into at least two edit classes, each edit class applying a different degree of an editing effect.
33. The non-transitory tangible computer readable media of claim 30 wherein the edit profile is determined by classifying the pixel properties into at least two edit classes, each edit class applying a different editing effect.
34. The non-transitory tangible computer readable media of claim 30 wherein the edit profile is determined by classifying the pixel properties using blind signal separation.
35. The non-transitory tangible computer readable media of claim 30 wherein the edit profile is determined by categorizing the pixel properties using a classifier.
36. The non-transitory tangible computer readable media of claim 30 wherein the edit profile is determined by classifying the pixel properties using discriminant analysis.
37. The non-transitory tangible computer readable media of claim 30 wherein the edit profile is determined by classifying the pixel properties using mixture modeling.
38. The non-transitory tangible computer readable media of claim 30 wherein the edit profile is determined by classifying the pixel properties using Bayesian statistics.
39. The non-transitory tangible computer readable media of claim 30 wherein the edit profile is determined by classifying the pixel properties using thresholds.
40. The non-transitory tangible computer readable media of claim 30 wherein the edit profile is determined by classifying the pixel properties using property variance.
41. The non-transitory tangible computer readable media of claim 30 wherein the edit profile includes overlapping edit classes, each edit class representing a different degree of editing effect.
42. The non-transitory tangible computer readable media of claim 30 wherein the edit profile includes overlapping edit classes, each edit class representing a different type of editing effect.
43. The non-transitory tangible computer readable media of claim 30 wherein the edit profile designates an edit class specifying a replacement value of an editable pixel property of the at least one pixel.
44. The non-transitory tangible computer readable media of claim 30 wherein the edit profile designates an edit class specifying a transformation of an editable pixel property of the at least one pixel.
45. The non-transitory tangible computer readable media of claim 26 wherein the editing operation comprises:
editing at least one pixel within each of the first predefined region and the second predefined region of the tool impression based on the first and second distributions of the pixel property.
46. The non-transitory tangible computer readable media of claim 26 wherein the pixel property is a composite pixel property.
47. The non-transitory tangible computer readable media of claim 26 wherein the pixel property is a multidimensional pixel property.
48. The non-transitory tangible computer readable media of claim 26 wherein the operation of sampling pixels in the first predefined region comprises:
determining a property value for each of a plurality of pixels within the first predefined region.
49. The non-transitory tangible computer readable media of claim 26 wherein the computer process further comprises:
determining location and dimensions of the tool impression within the digital image.
50. The non-transitory tangible computer readable media of claim 26 wherein the computer process further comprises:
identifying the pixels in the first predefined region within the tool impression of the digital image; and
identifying the pixels in the second predefined region within the tool impression of the digital image.
51. A system comprising:
a processor including:
a region sampling module that samples pixels in a first predefined region of a tool impression in a digital image to determine a first distribution of a pixel property of the pixels in the first predefined region and samples pixels in a second predefined region of the tool impression to determine a second distribution of the pixel property of the pixels in the second predefined region; and
an editing module that edits at least one pixel within the tool impression based on the first and second distributions.