Assisted 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 pixel property distributions. The property distributions from each region may be automatically 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 are represented by an edit profile, the generation of which may be completely automated based on selection of a tool impression, or partially automated using the selection of the tool impression and receipt of classification guidance input, such as one or more parameters received from user input or a configuration file. The edit classes may also be generated without reference to the pixel property distributions, such as via user input.
1. A method comprising:
sampling pixels within a first component region of a tool impression in a digital image;
determining a first distribution of a pixel property of the sampled pixels within the first component region;
sampling pixels within a second component region of the tool impression;
determining a second distribution of the pixel property of the sampled pixels within the second component region;
receiving a predetermined parameter that is independent of the distributions of the pixel property;
computing an adjustment factor based on the distribution of the pixel property using a processing unit, based upon both the first distribution and the second distribution;
computing an assisted tolerance parameter based on the adjustment factor and the predetermined parameter using the processing unit;
specifying one or more edit classes based upon the predetermined parameter and the assisted tolerance parameter, wherein the one or more edit classes define one or more respective subsets of the distribution; and
collectively editing all of a subset of the sampled pixels that correspond to one of the subsets of the distribution defined by a respective one of the edit classes by applying a same edit operation to each pixel in the subset of the sampled pixels using the processing unit.
2. The method of claim 1 wherein the receiving operation comprises:
receiving the predetermined parameter by user-specification through a user interface.
3. The method of claim 1 wherein the receiving operation comprises:
receiving the predetermined parameter from a configuration file.
4. The method of claim 1 further comprising:
deriving an edit profile characteristic based upon the distribution of the pixel property; and wherein
the editing operation edits the subset of the sampled pixels based upon the edit profile characteristic.
5. The method of claim 1 wherein the operation of computing an assisted tolerance parameter comprises:
scaling the predetermined parameter based on the adjustment factor to compute the assisted tolerance parameter.
6. The method of claim 1 further comprising:
generating an edit profile defining boundaries between the edit classes having a first threshold set by the predetermined parameter and a second threshold set by the assisted tolerance parameter, wherein the editing operation comprises editing the subset of the sampled pixels within the tool impression based on the edit profile.
7. The method of claim 6 wherein the first threshold designates a boundary between a partial edit class and an unchanged edit class.
8. The method of claim 6 wherein the second threshold designates a boundary between a full edit class and a partial edit class.
9. The method of claim 1 , wherein
the predetermined parameter defines a threshold between a first edit class and a second edit class; and
the assisted tolerance parameter defines a threshold between the second edit class and a third edit class.
10. One or more non-transitory computer-readable storage media storing a computer program for executing on a computer system a computer process, the computer process comprising:
sampling pixels within a first component region of a tool impression in a digital image;
determining a first distribution of a pixel property of the sampled pixels within the first component region;
sampling pixels within a second component region of the tool impression;
determining a second distribution of the pixel property of the sampled pixels within the second component region;
receiving a predetermined parameter that is independent of the distributions of the pixel property;
computing an adjustment factor based on the distribution of the pixel property based upon both the first distribution and the second distribution;
computing an assisted tolerance parameter based on the adjustment factor and the predetermined parameter;
specifying one or more edit classes based upon the predetermined parameter and the assisted tolerance parameter, wherein the one or more edit classes define one or more respective subsets of the distribution; and
collectively editing all of a subset of the sampled pixels that correspond to one of the subsets of the distribution defined by a respective one of the edit classes by applying a same edit operation to each pixel in the subset of the sampled pixels.
11. The non-transitory computer-readable storage media of claim 10 wherein the receiving operation comprises:
receiving the predetermined parameter by user-specification through a user interface.
12. The non-transitory computer-readable storage media of claim 10 wherein the receiving operation comprises:
receiving the predetermined parameter from a configuration file.
13. The non-transitory computer-readable storage media of claim 10 wherein the computer process further comprises:
deriving an edit profile characteristic based upon the distribution of the pixel property; and wherein
the editing operation edits the subset of the sampled pixels based upon the edit profile characteristic.
14. The non-transitory computer-readable storage media of claim 10 wherein the operation of computing an assisted tolerance parameter comprises:
scaling the predetermined parameter based on the adjustment factor to compute the assisted parameter.
15. The non-transitory computer-readable storage media of claim 10 wherein the computer process further comprises:
generating an edit profile defining boundaries between the edit classes having a first threshold set by the predetermined parameter and a second threshold set by the assisted tolerance parameter, wherein the editing operation comprises editing the subset of the sampled pixels within the tool impression based on the edit profile.
16. The non-transitory computer-readable storage media of claim 15 wherein the first threshold designates a boundary between a partial edit class and an unchanged edit class.
17. The non-transitory computer-readable storage media of claim 15 wherein the second threshold designates a boundary between a full edit class and a partial edit class.
18. The non-transitory computer-readable storage media of claim 10 , wherein
the predetermined parameter defines a threshold between a first edit class and a second edit class; and
the assisted tolerance parameter defines a threshold between the second edit class and a third edit class.
19. A computer system comprising:
a memory storing a region sampler module, an edit profile definition generator, and an editing module; and
a processor that implements
the region sampler module to sample pixels within a first component region of a tool impression in a digital image to determine a distribution of a pixel property of the sampled pixels within the first component region and to sample pixels within a second component region of the tool impression to determine a distribution of the pixel property of the sampled pixels within the second component region;
the edit profile definition generator to receive a parameter that is independent of the distributions of the pixel property, compute an adjustment factor based upon both the first distribution and the second distribution of the pixel property, compute an assisted tolerance parameter based on the adjustment factor and the parameter, and specify one or more edit classes based upon the parameter and the assisted tolerance parameter, wherein the one or more edit classes define one or more respective subsets of the distribution; and
the editing module to collectively edit all of a subset of the sampled pixels corresponding to one of the subsets of the distribution specified by a respective one of the edit classes by applying a same edit operation to each pixel in the subset of the sampled pixels.
20. A method of editing pixels in a specified region of a digital image, the specified region being defined by a tool impression, the method comprising:
sampling pixels within the tool impression in the digital image to determine a distribution of a pixel property of the pixels in the tool impression;
calculating a minimum tolerance parameter for an edit profile within the distribution using a processing unit;
calculating a maximum tolerance parameter for the edit profile within the distribution using the processing unit;
receiving a predefined tolerance parameter specifying a first alternative characteristic for the edit profile;
computing an assisted tolerance parameter as a function of the predefined tolerance parameter scaled by a ratio of the minimum tolerance parameter to the maximum tolerance parameter, wherein the assisted tolerance parameter specifies a second alternative characteristic for the edit profile using the processing unit;
establishing one or more edit classes based upon the predefined tolerance parameter and the assisted tolerance parameter, wherein the edit classes comprise subsets of the sampled pixels within the distribution; and
editing the sampled pixels within each edit class as groups according to the first and second alternative characteristics of the edit profile using the processing unit.
21. The method of claim 20 , wherein
the predefined tolerance parameter indicates a threshold between a first edit class and a second edit class; and
the assisted tolerance parameter indicates a threshold between the second edit class and a third edit class.